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

    Neuronpedia

    INDEX
    Explanations

    positional

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Japanese
    -0.07
    Pixels
    -0.07
    (random
    -0.07
     histo
    -0.07
     sens
    -0.07
    (Parser
    -0.07
    sparse
    -0.07
     theme
    -0.07
     kel
    -0.07
     driver
    -0.06
    POSITIVE LOGITS
    orphic
    0.08
     exacerb
    0.07
    最常见的
    0.07
    していた
    0.07
    最好不要
    0.07
     storefront
    0.06
     Loren
    0.06
    멓
    0.06
     entrenched
    0.06
    borg
    0.06
    Act Density 0.002%

    No Known Activations