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

    Neuronpedia

    INDEX
    Explanations

    context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uggage
    -0.07
    ерв
    -0.06
     protocols
    -0.06
    بيع
    -0.06
     слив
    -0.06
     іншого
    -0.06
     gastric
    -0.06
     السعودية
    -0.06
    ')");↵
    -0.06
     Kang
    -0.06
    POSITIVE LOGITS
    �
    0.07
    _FMT
    0.07
    erli
    0.07
    (md
    0.06
    hb
    0.06
     enormous
    0.06
    燕
    0.06
    hec
    0.06
     SUPER
    0.06
     impossible
    0.06
    Act Density 0.013%

    No Known Activations