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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Kodi
    -0.09
     miy
    -0.08
    Louis
    -0.08
    abling
    -0.08
    Pinterest
    -0.08
    ason
    -0.08
    reibt
    -0.08
    Showing
    -0.08
    picker
    -0.08
    Tf
    -0.08
    POSITIVE LOGITS
     fictional
    0.12
     fict
    0.11
     Doe
    0.09
     XYZ
    0.09
     Fiction
    0.09
     hypothetical
    0.09
    _secret
    0.09
     خط
    0.09
     hypot
    0.08
     Suppose
    0.08
    Act Density 1.502%

    No Known Activations