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

    Neuronpedia

    INDEX
    Explanations

    GetType or Access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PathComponent
    0.86
     motivos
    0.84
     τον
    0.82
     commentaries
    0.82
     rasgos
    0.80
     लकार
    0.79
     fundamentos
    0.77
     slags
    0.77
     tokamaks
    0.77
     componentes
    0.77
    POSITIVE LOGITS
    ли
    0.82
    liance
    0.82
    ت
    0.78
    ating
    0.75
     Ді
    0.74
    ي
    0.74
    芠
    0.73
    et
    0.73
    erté
    0.71
    María
    0.71
    Act Density 0.001%

    No Known Activations