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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    frog
    -0.07
     hatred
    -0.07
     requestCode
    -0.06
    ÜRK
    -0.06
     seine
    -0.06
     UIS
    -0.06
    uppe
    -0.06
    AlertDialog
    -0.06
    .Replace
    -0.06
    ούν
    -0.06
    POSITIVE LOGITS
    Affected
    0.07
    Mos
    0.06
     을
    0.06
     ")"
    0.06
    _IDX
    0.06
     तल
    0.06
    نين
    0.06
     Motorcycle
    0.06
    cih
    0.06
    Compatible
    0.06
    Act Density 0.031%

    No Known Activations