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

    Neuronpedia

    INDEX
    Explanations

    Code/technical content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    맥
    -0.06
    001
    -0.06
    avad
    -0.06
    CON
    -0.06
    coop
    -0.06
     Wak
    -0.06
    -card
    -0.06
    entů
    -0.06
    .variable
    -0.06
    010
    -0.06
    POSITIVE LOGITS
    _batches
    0.07
     gt
    0.07
    ágenes
    0.06
     기간
    0.06
     gritty
    0.06
     logistical
    0.06
     [`
    0.06
     grupo
    0.06
    imary
    0.06
    ，我们
    0.06
    Act Density 0.000%

    No Known Activations