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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _PH
    -0.07
    运
    -0.06
    黒
    -0.06
    Sup
    -0.06
    ::::::
    -0.06
     endforeach
    -0.06
     обо
    -0.06
     fint
    -0.06
    model
    -0.06
     impeachment
    -0.06
    POSITIVE LOGITS
    .has
    0.07
     شناس
    0.06
    “In
    0.06
    .align
    0.06
    adjust
    0.06
     triumph
    0.06
    psc
    0.06
    "They
    0.06
     optics
    0.06
     etmiştir
    0.06
    Act Density 0.014%

    No Known Activations