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

    Neuronpedia

    INDEX
    Explanations

    miscellaneous

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    十一
    -0.07
     редак
    -0.06
     teşekkür
    -0.06
    -paying
    -0.06
     serious
    -0.06
    被
    -0.06
    @Slf
    -0.06
    风险
    -0.06
    .Release
    -0.06
     списка
    -0.06
    POSITIVE LOGITS
     oblivious
    0.06
    ump
    0.06
    fullname
    0.06
    blems
    0.06
    戲
    0.06
    backs
    0.06
    迷
    0.06
    _that
    0.06
     Heights
    0.06
     afs
    0.06
    Act Density 0.000%

    No Known Activations