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

    Neuronpedia

    INDEX
    Explanations

    ;

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fib
    -0.07
    124
    -0.07
     HM
    -0.07
    rophic
    -0.06
    ��
    -0.06
    attice
    -0.06
     Sutton
    -0.06
     busted
    -0.06
    Matrix
    -0.06
     rpt
    -0.06
    POSITIVE LOGITS
    .sub
    0.07
     advantageous
    0.07
    >e
    0.06
    orious
    0.06
    email
    0.06
    <l
    0.06
     texas
    0.06
     restau
    0.06
     Bud
    0.06
     schw
    0.06
    Act Density 0.020%

    No Known Activations