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

    Neuronpedia

    INDEX
    Explanations

    add

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ющ
    -0.07
     Creature
    -0.07
    HasMaxLength
    -0.07
     drv
    -0.06
    매
    -0.06
    were
    -0.06
     моря
    -0.06
    ##↵↵
    -0.06
    iven
    -0.06
    ρι
    -0.06
    POSITIVE LOGITS
     fork
    0.07
    OCK
    0.06
     guess
    0.06
     closing
    0.06
     Κ
    0.06
     “[
    0.06
     FF
    0.06
    ()["
    0.06
     LOCK
    0.06
     NEWS
    0.06
    Act Density 0.019%

    No Known Activations