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

    Neuronpedia

    INDEX
    Explanations

    fail

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (param
    -0.07
     Exterior
    -0.07
     viral
    -0.07
     prote
    -0.07
    ieron
    -0.06
     Dup
    -0.06
     CT
    -0.06
    (Config
    -0.06
     Jud
    -0.06
    تری
    -0.06
    POSITIVE LOGITS
    undreds
    0.07
     Sage
    0.07
    ？」↵↵
    0.06
     Pink
    0.06
    avatars
    0.06
    .tools
    0.06
    cosity
    0.06
    donnees
    0.06
    徒歩
    0.06
     výši
    0.06
    Act Density 0.239%

    No Known Activations