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

    Neuronpedia

    INDEX
    Explanations

    sharing information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    300
    -0.07
    pose
    -0.07
    hora
    -0.06
    める
    -0.06
    meaning
    -0.06
     bleiben
    -0.06
    -performance
    -0.06
     Gee
    -0.06
     XOR
    -0.06
     curator
    -0.06
    POSITIVE LOGITS
    _ASM
    0.07
    pgsql
    0.07
     inscription
    0.07
    来源
    0.06
     getState
    0.06
    .EX
    0.06
    ีพ
    0.06
     FString
    0.06
     lawsuit
    0.06
    .esp
    0.06
    Act Density 0.004%

    No Known Activations