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

    Neuronpedia

    INDEX
    Explanations

    Dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (SC
    -0.06
    coni
    -0.06
    -DD
    -0.06
    _MED
    -0.06
    .identity
    -0.06
     Sew
    -0.06
    51
    -0.05
     cpf
    -0.05
     无
    -0.05
    	FOR
    -0.05
    POSITIVE LOGITS
    attached
    0.07
    TOP
    0.07
     ;
↵
    0.07
    script
    0.07
     pan
    0.07
    serie
    0.06
    書
    0.06
    办理
    0.06
    弱
    0.06
     prend
    0.06
    Act Density 0.015%

    No Known Activations