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

    Neuronpedia

    INDEX
    Explanations

    non-English snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    classmethod
    -0.07
    $string
    -0.06
    mite
    -0.06
    zoom
    -0.06
    .Subscribe
    -0.06
    Т
    -0.06
    шт
    -0.06
     osoby
    -0.06
     вещества
    -0.06
    ์ต
    -0.06
    POSITIVE LOGITS
     path
    0.07
    _bed
    0.07
     induced
    0.06
     command
    0.06
     handed
    0.06
     href
    0.06
    -S
    0.06
     raced
    0.06
    .AC
    0.06
     hospital
    0.06
    Act Density 0.082%

    No Known Activations