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

    Neuronpedia

    INDEX
    Explanations

    needing more

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Way
    -0.59
     Needed
    -0.51
    Required
    -0.50
    dymyr
    -0.50
    InSection
    -0.49
     OMITBAD
    -0.49
    required
    -0.49
     Required
    -0.49
    rrggbb
    -0.48
    jdt
    -0.47
    POSITIVE LOGITS
     Monfieur
    0.74
     Provid
    0.66
     Theſe
    0.65
     ―――――
    0.64
     themſelves
    0.62
     myſelf
    0.60
    URLException
    0.60
     whoſe
    0.59
     Efq
    0.57
     ſtill
    0.57
    Act Density 0.434%

    No Known Activations