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

    Neuronpedia

    INDEX
    Explanations

    approaches and methods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ότε
    -0.07
    ोजन
    -0.06
    _Item
    -0.06
    ighton
    -0.06
    Ray
    -0.06
    <Boolean
    -0.06
     defin
    -0.06
    �
    -0.06
     mun
    -0.06
     asshole
    -0.06
    POSITIVE LOGITS
    ONGO
    0.07
    eşit
    0.07
     allies
    0.06
     трансп
    0.06
     обра
    0.06
    ažd
    0.06
    _likes
    0.06
    ajor
    0.06
    ське
    0.06
     xnxx
    0.06
    Act Density 0.104%

    No Known Activations