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

    Neuronpedia

    INDEX
    Explanations

    output from code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uf
    0.64
     tohoto
    0.62
     Dong
    0.61
    ist
    0.59
     acest
    0.59
    t
    0.58
    UR
    0.58
     دیگر
    0.57
     هذا
    0.56
    志森
    0.55
    POSITIVE LOGITS
    a
    0.58
     the
    0.57
    な
    0.55
    the
    0.55
    ция
    0.55
     inertial
    0.54
     freezing
    0.54
     pampered
    0.54
     output
    0.53
     milking
    0.52
    Act Density 0.001%

    No Known Activations