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

    Neuronpedia

    INDEX
    Explanations

    is expected

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dioxane
    0.94
    ﺠ
    0.93
     cellSize
    0.84
     neur
    0.82
     scegliere
    0.82
     teatral
    0.82
     mannit
    0.81
     sputum
    0.80
     sektor
    0.79
    ﻜ
    0.79
    POSITIVE LOGITS
    icking
    0.77
    the
    0.76
    osten
    0.75
    Int
    0.74
    ides
    0.71
    Battle
    0.70
    rik
    0.69
    ensing
    0.68
    ocl
    0.68
    CLK
    0.68
    Act Density 0.000%

    No Known Activations