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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .driver
    -0.09
     safety
    -0.07
    _ly
    -0.07
     to
    -0.07
    .bc
    -0.07
    _cluster
    -0.07
     steep
    -0.07
    ادية
    -0.06
     Dynasty
    -0.06
    >
    -0.06
    POSITIVE LOGITS
     utilisateur
    0.07
     challenger
    0.06
     sürekli
    0.06
     Melbourne
    0.06
    ORTH
    0.06
    itled
    0.05
     Verd
    0.05
     örnek
    0.05
     elabor
    0.05
    Foto
    0.05
    Act Density 0.026%

    No Known Activations