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

    Neuronpedia

    INDEX
    Explanations

    中

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    іг
    -0.06
     baked
    -0.06
    .Debugger
    -0.06
    FORMATION
    -0.06
    令人
    -0.06
    .cm
    -0.06
     sie
    -0.06
    ้อน
    -0.06
    Profiler
    -0.06
    oui
    -0.06
    POSITIVE LOGITS
    errar
    0.07
     Dim
    0.07
    onestly
    0.06
     приклад
    0.06
    Contr
    0.06
     aplic
    0.06
     Valk
    0.06
     bloody
    0.06
     Arab
    0.06
     mutate
    0.06
    Act Density 0.001%

    No Known Activations