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

    Neuronpedia

    INDEX
    Explanations

    finding details and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wordpress
    0.43
     wordpress
    0.39
    wordpress
    0.39
    に残
    0.39
     염
    0.38
    残留
    0.38
     integrand
    0.38
    ogluc
    0.38
    resultlist
    0.38
    ometimes
    0.38
    POSITIVE LOGITS
    Tram
    0.42
     ladder
    0.42
    UW
    0.39
     vaš
    0.39
    tram
    0.39
     trampoline
    0.38
    ONE
    0.36
     вашем
    0.36
     cabang
    0.36
    HALL
    0.36
    Act Density 0.000%

    No Known Activations