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

    Neuronpedia

    INDEX
    Explanations

    instructed or required

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ี
    1.00
    own
    0.82
    am
    0.82
    if
    0.80
    राला
    0.74
     magnified
    0.74
    ze
    0.71
    ן
    0.71
    주는
    0.71
    owne
    0.71
    POSITIVE LOGITS
    കൻ
    0.81
     եւ
    0.81
     viaje
    0.78
    Política
    0.78
    meshes
    0.78
     sensibles
    0.77
     españa
    0.74
     casilla
    0.73
    dea
    0.73
    స్కీ
    0.72
    Act Density 0.000%

    No Known Activations