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

    Neuronpedia

    INDEX
    Explanations

    technical terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     occupied
    0.71
    WallArray
    0.69
     kvar
    0.69
    とともに
    0.68
    捷
    0.67
     occupies
    0.67
     abducted
    0.66
     Monte
    0.65
     contaminating
    0.64
     church
    0.64
    POSITIVE LOGITS
    tooltip
    0.79
    urist
    0.78
    g
    0.77
    iological
    0.75
    banners
    0.73
    Threat
    0.73
    UserInfo
    0.72
    retrofit
    0.72
    kotlin
    0.71
    o
    0.70
    Act Density 0.000%

    No Known Activations