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

    Neuronpedia

    INDEX
    Explanations

    loading files and resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     incumpl
    0.77
     depositors
    0.71
    va
    0.70
    cedes
    0.70
    দিন
    0.69
    daar
    0.69
    ycle
    0.68
     način
    0.67
    ggle
    0.66
    घर
    0.66
    POSITIVE LOGITS
    ET
    0.71
    ずっと
    0.70
    الم
    0.68
    ある
    0.67
     kutoka
    0.67
    ารย์
    0.67
     সবার
    0.65
    一人
    0.64
    𝗕
    0.63
     относя
    0.63
    Act Density 0.000%

    No Known Activations