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

    Neuronpedia

    INDEX
    Explanations

    Programming history

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    analy
    -0.06
     ostensibly
    -0.06
     directives
    -0.06
    -chevron
    -0.06
    ารถ
    -0.06
     dry
    -0.06
    찌
    -0.06
    (tc
    -0.05
     absorb
    -0.05
    適用
    -0.05
    POSITIVE LOGITS
    mak
    0.07
     βασ
    0.07
    нет
    0.07
    ').↵
    0.07
     total
    0.07
    EL
    0.06
    >{{$
    0.06
    мин
    0.06
     herkes
    0.06
    _classes
    0.06
    Act Density 0.045%

    No Known Activations