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

    Neuronpedia

    INDEX
    Explanations

    untreated/unchecked

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     untreated
    -0.97
     unused
    -0.88
     unchecked
    -0.71
     Unused
    -0.68
    Unused
    -0.66
     neglected
    -0.65
     untouched
    -0.63
     unattended
    -0.60
     unfinished
    -0.56
     untapped
    -0.56
    POSITIVE LOGITS
     Normdatei
    0.93
     initComponents
    0.82
    aarrggbb
    0.75
    ReusableCell
    0.70
     '\\;'
    0.69
     AssemblyProduct
    0.69
     légales
    0.69
    autorest
    0.69
    ThroughAttribute
    0.68
    তথ্যসূত্র
    0.66
    Act Density 0.155%

    No Known Activations