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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bloom
    -0.08
    血
    -0.07
    _smart
    -0.07
     trùng
    -0.07
     target
    -0.07
    ดา
    -0.07
    大爷
    -0.07
     wrote
    -0.07
    pers
    -0.07
    _Update
    -0.07
    POSITIVE LOGITS
    хот
    0.08
    ://"
    0.07
     '%"
    0.07
     yüzde
    0.06
    Utf
    0.06
     그런
    0.06
    لازم
    0.06
     기본
    0.06
     여러
    0.06
    �
    0.06
    Act Density 0.007%

    No Known Activations