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

    Neuronpedia

    INDEX
    Explanations

    Pronouns

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the verb “ask,” i.e. it detects explicit requests.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    sn
    -0.07
     Robot
    -0.06
    _note
    -0.06
     sm
    -0.06
    rit
    -0.06
    XM
    -0.06
     mænd
    -0.06
    AllowAnonymous
    -0.06
    _kses
    -0.06
     Lyons
    -0.06
    POSITIVE LOGITS
    .readLine
    0.07
     asymmetric
    0.06
     obedient
    0.06
    ↵↵↵↵↵↵↵↵↵
    0.06
     added
    0.06
     questa
    0.06
    ":"+
    0.06
    'use
    0.06
    قر
    0.06
    _opcode
    0.06
    Act Density 0.010%

    No Known Activations