Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Scheduling/time

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens that are part of scheduling times (e.g. hour/minute expressions like “10 h 00,” “14 h 30,” and related labels such as “Personne” followed by a time), i.e. it detects time‐slot entries.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     equip
    -0.07
     Commands
    -0.06
    'RE
    -0.06
    /tty
    -0.06
    bron
    -0.06
     '');↵
    -0.06
    iagnostics
    -0.06
     pens
    -0.06
    iterals
    -0.06
     Fleming
    -0.05
    POSITIVE LOGITS
    άς
    0.08
    0.07
     authService
    0.07
    ●●
    0.07
    không
    0.07
    /problem
    0.07
    signin
    0.07
    >");
↵
    0.06
    .DataGridViewContentAlignment
    0.06
     disag
    0.06
    Act Density 0.019%

    No Known Activations