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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     زن
    -0.07
     assass
    -0.07
     Αλ
    -0.07
    =<?=
    -0.06
     building
    -0.06
     Difference
    -0.06
     Though
    -0.06
     extend
    -0.06
     Irvine
    -0.06
     있던
    -0.06
    POSITIVE LOGITS
    _br
    0.06
    kat
    0.06
     Metro
    0.06
    óg
    0.06
     pomoci
    0.06
    pect
    0.06
    าะห
    0.06
    intestinal
    0.06
    lr
    0.06
     UNIQUE
    0.06
    Act Density 0.181%

    No Known Activations