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

    Neuronpedia

    INDEX
    Explanations

    model response start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     instantiate
    0.79
     identically
    0.74
     מר
    0.73
     Equivalent
    0.66
     dezelfde
    0.66
     quartic
    0.65
     tương
    0.63
    дови
    0.63
    chun
    0.61
     instantiation
    0.61
    POSITIVE LOGITS
    Several
    0.82
    There
    0.80
    several
    0.79
    there
    0.79
    hacking
    0.77
    勺
    0.75
     هناك
    0.72
     outages
    0.72
     There
    0.72
    шире
    0.72
    Act Density 0.106%

    No Known Activations