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

    Neuronpedia

    INDEX
    Explanations

    multilingual characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rid
    0.81
     growers
    0.81
    rated
    0.79
     toán
    0.78
    igating
    0.77
    cB
    0.77
     pedir
    0.76
     eup
    0.74
    küm
    0.73
     Negeri
    0.73
    POSITIVE LOGITS
    я
    0.80
    گر
    0.76
    짱
    0.75
    נם
    0.74
    ן
    0.73
    수
    0.72
    յ
    0.71
    ное
    0.70
    ش
    0.70
    ই
    0.69
    Act Density 0.001%

    No Known Activations