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

    Neuronpedia

    INDEX
    Explanations

    website/document information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     attracts
    -0.07
    ooky
    -0.07
     soruml
    -0.07
     스포츠
    -0.07
    Ố
    -0.06
     стандарт
    -0.06
     motions
    -0.06
    (plugin
    -0.06
     Morph
    -0.06
    وله
    -0.06
    POSITIVE LOGITS
    AGING
    0.07
     unge
    0.06
    argc
    0.06
     sitesinde
    0.06
     tamam
    0.06
     ham
    0.06
     Marker
    0.06
    DED
    0.06
     zástup
    0.06
    oplayer
    0.06
    Act Density 0.036%

    No Known Activations