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

    Neuronpedia

    INDEX
    Explanations

    Qualifying statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     handful
    -0.68
    red
    -0.67
     grid
    -0.66
    -0.63
    piracy
    -0.62
     Starter
    -0.59
     toe
    -0.59
     hjælp
    -0.56
    AsUp
    -0.56
    OGND
    -0.56
    POSITIVE LOGITS
    fjspx
    0.53
    enumii
    0.51
     dovuto
    0.49
    InSection
    0.48
     snippetHide
    0.48
     favour
    0.47
     decimals
    0.47
    TRL
    0.46
    ('*',
    0.46
    ../../
    0.45
    Act Density 0.134%

    No Known Activations