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

    Neuronpedia

    INDEX
    Explanations

    is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     familiarize
    0.88
     território
    0.84
    t
    0.81
    ší
    0.79
     Clas
    0.79
    ﻥ
    0.79
     hệ
    0.78
     finalizing
    0.78
     بِ
    0.77
    alámb
    0.77
    POSITIVE LOGITS
    PT
    0.79
    .
    0.77
    $('.
    0.76
    OP
    0.73
    wh
    0.72
    TT
    0.71
     oyo
    0.70
    Bucket
    0.70
    AV
    0.70
    OA
    0.68
    Act Density 0.001%

    No Known Activations