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

    Neuronpedia

    INDEX
    Explanations

    version

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ('~
    -0.06
    stk
    -0.06
    ыш
    -0.06
    oran
    -0.06
     정보
    -0.06
     sharks
    -0.06
    _PAIR
    -0.06
    strpos
    -0.05
    มต
    -0.05
     Mourinho
    -0.05
    POSITIVE LOGITS
    queda
    0.07
     meine
    0.07
    ไซ
    0.07
    386
    0.06
    čku
    0.06
    íž
    0.06
     outf
    0.06
     Reload
    0.06
    ा:
    0.06
     converter
    0.06
    Act Density 0.000%

    No Known Activations