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

    Neuronpedia

    INDEX
    Explanations

    URL paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cobran
    0.87
     domanda
    0.86
     проду
    0.83
     aportar
    0.83
    แปลง
    0.82
     demikian
    0.82
     ain
    0.78
     واست
    0.77
    ilibre
    0.77
    olve
    0.77
    POSITIVE LOGITS
    geke
    0.82
    g
    0.82
    arctic
    0.79
    大的
    0.76
     Cicero
    0.76
    行
    0.75
    行って
    0.74
    先輩
    0.73
     sovereignty
    0.73
    contentType
    0.71
    Act Density 0.003%

    No Known Activations