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

    Neuronpedia

    INDEX
    Explanations

    software

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inesis
    -0.07
    录
    -0.07
     organism
    -0.07
     Degree
    -0.06
     billionaires
    -0.06
     hern
    -0.06
     نخست
    -0.06
     fk
    -0.06
    jeme
    -0.06
     Prosec
    -0.06
    POSITIVE LOGITS
     รอง
    0.06
    _BOOL
    0.06
     NPC
    0.06
     lake
    0.06
     Nisan
    0.06
    .Operator
    0.06
    LC
    0.06
    ै.↵
    0.06
     Rencontres
    0.06
     其他
    0.06
    Act Density 0.001%

    No Known Activations