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

    Neuronpedia

    INDEX
    Explanations

    Property

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :The
    -0.07
     supports
    -0.07
    courses
    -0.07
    _HEIGHT
    -0.07
    時点で
    -0.07
    纾
    -0.07
     связ
    -0.07
     either
    -0.07
    𬬿
    -0.06
     reporters
    -0.06
    POSITIVE LOGITS
    ԝ
    0.08
    _weapon
    0.07
    POOL
    0.07
    /in
    0.06
    '{
    0.06
    ={↵
    0.06
    serir
    0.06
    愈加
    0.06
    _metric
    0.06
    .timestamp
    0.06
    Act Density 0.001%

    No Known Activations