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

    Neuronpedia

    INDEX
    Explanations

    10

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prostit
    -0.07
    हन
    -0.07
    blr
    -0.07
     teen
    -0.07
    flight
    -0.06
    urrences
    -0.06
    fil
    -0.06
    bairro
    -0.06
    drink
    -0.06
     fant
    -0.06
    POSITIVE LOGITS
    0.07
     historian
    0.07
    "testing
    0.06
    402
    0.06
    ++){
    0.06
     Secondary
    0.06
    0.06
     Increased
    0.06
    0.06
     loadImage
    0.06
    Act Density 0.008%

    No Known Activations