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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Chairs
    -0.07
     Lista
    -0.07
    ayas
    -0.07
     exports
    -0.06
    .retrieve
    -0.06
    orque
    -0.06
    .ib
    -0.06
    las
    -0.06
    hip
    -0.06
     TMZ
    -0.06
    POSITIVE LOGITS
     Gone
    0.07
    Gradient
    0.07
     giveaway
    0.07
    ्ध
    0.07
     numerator
    0.07
     vest
    0.07
     electro
    0.06
     slapped
    0.06
     gave
    0.06
    ceptor
    0.06
    Act Density 0.000%

    No Known Activations