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

    Neuronpedia

    INDEX
    Explanations

    56

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    reta
    0.64
     racetr
    0.64
    oop
    0.63
    getPackageName
    0.62
    photon
    0.62
    rnn
    0.61
    diyl
    0.61
    elisk
    0.61
    issati
    0.60
     viewer
    0.60
    POSITIVE LOGITS
    อาการ
    0.80
    袭击
    0.72
     nonspecific
    0.69
     prophylaxis
    0.68
     milestone
    0.67
     تعین
    0.66
     Gust
    0.65
     therapy
    0.65
     মাহবুব
    0.65
    大全
    0.64
    Act Density 0.003%

    No Known Activations