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

    Neuronpedia

    INDEX
    Explanations

    both

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     progressing
    -0.07
     digest
    -0.07
    Trust
    -0.07
     Tk
    -0.07
    Fresh
    -0.07
     blur
    -0.07
    much
    -0.06
    entication
    -0.06
     Hod
    -0.06
    Pl
    -0.06
    POSITIVE LOGITS
    _iff
    0.07
    ço
    0.07
     inFile
    0.07
     dział
    0.06
     перепис
    0.06
    ÃO
    0.06
    /values
    0.06
    .ExecuteScalar
    0.06
     пів
    0.06
     dès
    0.06
    Act Density 0.037%

    No Known Activations