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

    Neuronpedia

    INDEX
    Explanations

    http status codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     returned
    0.45
     payback
    0.43
     ошибок
    0.43
     दीवार
    0.42
    ToServer
    0.42
     Beside
    0.41
    报错
    0.41
    返回值
    0.41
     वेबसाइट
    0.40
    Redirect
    0.40
    POSITIVE LOGITS
    ições
    0.41
    ín
    0.40
    CHES
    0.38
     Str
    0.36
     Res
    0.36
     هل
    0.35
    层的
    0.35
     pará
    0.35
    プション
    0.35
     Sf
    0.35
    Act Density 0.002%

    No Known Activations