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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    usters
    -0.07
     amour
    -0.07
     constants
    -0.07
     homosexuality
    -0.07
    Padding
    -0.07
     retail
    -0.07
     rotation
    -0.07
    env
    -0.07
     elsewhere
    -0.07
    ilateral
    -0.07
    POSITIVE LOGITS
    @Table
    0.07
    Blog
    0.07
     edilmiş
    0.06
    (gt
    0.06
     вваж
    0.06
     wei
    0.06
     tend
    0.06
    -visible
    0.06
    (mapped
    0.06
    ND
    0.06
    Act Density 0.041%

    No Known Activations