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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PIPE
    -0.07
     функци
    -0.06
    981
    -0.06
    :w
    -0.06
     нес
    -0.06
    姆
    -0.06
    azo
    -0.06
     top
    -0.06
    ictim
    -0.06
     Woo
    -0.06
    POSITIVE LOGITS
    ');");↵
    0.07
    .`);↵
    0.07
    .getInstance
    0.07
     �
    0.06
    /'↵
    0.06
    ）。↵
    0.06
     wield
    0.06
     cherish
    0.06
    lášení
    0.06
     }]↵
    0.06
    Act Density 0.058%

    No Known Activations