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

    Neuronpedia

    INDEX
    Explanations

    `public`

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	found
    -0.07
    nesty
    -0.07
    Seen
    -0.07
    suggest
    -0.06
    Mother
    -0.06
    
    -0.06
    Discount
    -0.06
     thử
    -0.06
    night
    -0.06
    -device
    -0.06
    POSITIVE LOGITS
    .AllowUser
    0.08
     передбач
    0.08
     уд
    0.07
    APolynomial
    0.07
     Buddh
    0.06
    melon
    0.06
    θος
    0.06
     ویژگی
    0.06
    .multi
    0.06
     така
    0.06
    Act Density 0.020%

    No Known Activations