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

    Neuronpedia

    INDEX
    Explanations

    pre

    np_max-act · gemini-2.0-flash

    The neuron is triggered by tokens representing floating‐point numbers (decimal values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    drops
    -0.07
    ลด
    -0.07
    nist
    -0.06
     Held
    -0.06
    _abs
    -0.06
    桥
    -0.06
    Vien
    -0.06
    IRECT
    -0.06
    herent
    -0.06
     Ernest
    -0.06
    POSITIVE LOGITS
     inkl
    0.08
    BE
    0.06
     regulating
    0.06
     overseeing
    0.06
    *,
    0.06
     monarchy
    0.06
    configuration
    0.06
     ging
    0.06
     licensing
    0.06
    \F
    0.06
    Act Density 0.000%

    No Known Activations