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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ❤
    -0.09
     Worcester
    -0.08
     Himal
    -0.08
     �
    -0.08
     entfer
    -0.08
     stole
    -0.08
     toimit
    -0.08
     స్వ
    -0.08
     Свят
    -0.07
     walnuts
    -0.07
    POSITIVE LOGITS
    ·
    0.08
    ाना
    0.07
    trans
    0.07
    0.07
    Firstly
    0.07
     circumstances
    0.07
    Trans
    0.07
    .address
    0.07
    .trans
    0.07
    antic
    0.07
    Act Density 0.001%
    No Known Activations