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
    mmas
    -0.08
    Eat
    -0.07
    nergie
    -0.07
    Producer
    -0.06
    (api
    -0.06
     padx
    -0.06
     collider
    -0.06
    curity
    -0.06
    bindung
    -0.06
     beams
    -0.06
    POSITIVE LOGITS
    }}↵↵
    0.07
    格式
    0.06
    "/>↵
    0.06
    ?>↵↵
    0.06
    ै।↵
    0.06
    ?>
    0.06
     {}),↵
    0.06
    /.↵↵
    0.06
     '))↵
    0.06
    ()}↵
    0.06
    Act Density 0.000%

    No Known Activations