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
    Addresses
    -0.07
    ней
    -0.07
    hill
    -0.06
     noop
    -0.06
     رضا
    -0.06
     imageSize
    -0.06
    /Delete
    -0.06
     gör
    -0.06
    :key
    -0.06
     усіх
    -0.06
    POSITIVE LOGITS
    plus
    0.07
    FILENAME
    0.06
    (crate
    0.06
     Gro
    0.06
    formulario
    0.06
     ऐस
    0.06
     dramatic
    0.06
    .context
    0.06
     likelihood
    0.06
     minority
    0.05
    Act Density 0.030%

    No Known Activations