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

    Neuronpedia

    INDEX
    Explanations

    end of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ক
    0.63
    nabi
    0.52
    ❏
    0.52
    রী
    0.51
    be
    0.48
    vindos
    0.48
    ecek
    0.47
    سپ
    0.47
    ه
    0.47
    ivated
    0.47
    POSITIVE LOGITS
     договор
    0.49
     races
    0.49
     predictability
    0.47
     precincts
    0.46
     ordeal
    0.46
     imposes
    0.45
    Deviation
    0.45
     взгля
    0.45
    Highest
    0.45
    getAction
    0.44
    Act Density 0.008%

    No Known Activations