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

    Neuronpedia

    INDEX
    Explanations

    future dates/targets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    можно
    -0.08
     same
    -0.08
    メント
    -0.07
     refute
    -0.07
    无
    -0.07
    阑
    -0.07
    FieldName
    -0.07
    ン
    -0.07
     all
    -0.07
    izando
    -0.07
    POSITIVE LOGITS
    :S
    0.07
     distributors
    0.07
    ☛
    0.07
    땃
    0.07
     distrib
    0.07
     preorder
    0.07
    //:
    0.06
     sweets
    0.06
    tractor
    0.06
     nim
    0.06
    Act Density 0.004%

    No Known Activations