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

    Neuronpedia

    INDEX
    Explanations

    code splitting and data parsing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    【
    0.80
    ILO
    0.75
    に
    0.69
    相
    0.69
    विजन
    0.68
    ppe
    0.67
    格子
    0.67
    कार
    0.66
    INT
    0.66
    英語
    0.66
    POSITIVE LOGITS
     phosphoryl
    1.05
     Weyl
    0.85
     cortisol
    0.83
     хранения
    0.82
     použí
    0.81
     postulated
    0.81
     نە
    0.81
     homozyg
    0.81
     thermodynamics
    0.79
    로부터
    0.79
    Act Density 0.000%

    No Known Activations