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

    Neuronpedia

    INDEX
    Explanations

    F

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     :|
    -0.07
    ,time
    -0.07
    ,,
    -0.07
    Plain
    -0.06
    .↵↵↵↵
    -0.06
    ])↵↵↵
    -0.06
    名字
    -0.06
    Analyzer
    -0.06
     часто
    -0.06
    ,email
    -0.06
    POSITIVE LOGITS
     premiums
    0.07
     steel
    0.06
    東
    0.06
    (svg
    0.06
     fiery
    0.06
     Funding
    0.06
     truncate
    0.06
     broadcasting
    0.06
     threatens
    0.06
     proceeds
    0.06
    Act Density 0.001%

    No Known Activations