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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Narrow
    -0.08
    (Link
    -0.07
     Relax
    -0.06
    虽然
    -0.06
     proceso
    -0.06
     newPassword
    -0.06
    nio
    -0.06
     motorcycles
    -0.06
    _hidden
    -0.06
     Wo
    -0.06
    POSITIVE LOGITS
    }});↵
    0.06
     تغ
    0.06
    >';
↵
    0.06
     mimo
    0.06
    ไฟฟ
    0.06
    }@
    0.06
    　ゝ
    0.06
    	flags
    0.06
    드
    0.06
    理
    0.06
    Act Density 0.524%

    No Known Activations