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

    Neuronpedia

    INDEX
    Explanations

    A

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sam
    -0.08
     Formatter
    -0.07
    .dirty
    -0.07
    -threatening
    -0.07
    �
    -0.07
    .ActionEvent
    -0.06
    ‖
    -0.06
    stmt
    -0.06
    <n
    -0.06
    ,↵↵↵↵
    -0.06
    POSITIVE LOGITS
    耀
    0.09
    גה
    0.08
     Gerard
    0.07
    쨌
    0.07
    ocom
    0.07
    oids
    0.06
    UB
    0.06
     Garland
    0.06
    기는
    0.06
     podemos
    0.06
    Act Density 0.000%

    No Known Activations