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
     stairs
    -0.07
     borrow
    -0.07
     responses
    -0.06
    (SK
    -0.06
     shall
    -0.06
     underestimate
    -0.06
    $error
    -0.06
    ==>
    -0.06
     Ras
    -0.06
    격
    -0.06
    POSITIVE LOGITS
    violent
    0.06
    708
    0.06
    �
    0.06
    941
    0.06
    Squared
    0.06
    67
    0.06
     εργ
    0.06
    coin
    0.06
    haft
    0.06
    164
    0.06
    Act Density 0.000%

    No Known Activations