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

    Neuronpedia

    INDEX
    Explanations

    با

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    疾
    -0.08
    544
    -0.08
     alk
    -0.08
     Alk
    -0.08
     �
    -0.08
    Paul
    -0.08
     tá
    -0.08
     sulfur
    -0.08
     �
    -0.08
    nement
    -0.07
    POSITIVE LOGITS
     certainty
    0.07
     Wealth
    0.07
     bipolar
    0.07
    ாத
    0.07
     Bip
    0.07
     Fountain
    0.07
    券
    0.07
     ധ
    0.07
     Harper
    0.07
    قامة
    0.07
    Act Density 0.003%

    No Known Activations