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

    Neuronpedia

    INDEX
    Explanations

    more

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     consts
    -0.07
     ------------------------------------------------------------------------------------------------
    -0.06
     Stra
    -0.06
     Chuck
    -0.06
    (padding
    -0.06
    	from
    -0.06
     }
↵
↵
    -0.06
    format
    -0.06
     frustration
    -0.06
    Communication
    -0.06
    POSITIVE LOGITS
    获
    0.07
    ประโย
    0.07
     �
    0.07
    議
    0.06
    ơi
    0.06
    uez
    0.06
    elog
    0.06
    рії
    0.06
    Lf
    0.06
    .Me
    0.06
    Act Density 0.073%

    No Known Activations