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

    Neuronpedia

    INDEX
    Explanations

    doing something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     not
    1.13
     sebaik
    0.86
     Not
    0.86
     nicht
    0.82
    Not
    0.81
    ട്
    0.81
    not
    0.81
    ủng
    0.80
     זאת
    0.78
     SDLK
    0.75
    POSITIVE LOGITS
     ropes
    0.98
    𝗲
    0.97
     rope
    0.93
    el
    0.89
    പ്പുറ
    0.81
    al
    0.80
    how
    0.79
    льский
    0.78
    𝗮
    0.77
     paraphernalia
    0.76
    Act Density 0.011%

    No Known Activations