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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     coleg
    -0.07
     Salon
    -0.07
    .press
    -0.07
     phosphate
    -0.07
     SAL
    -0.06
    WITH
    -0.06
    _Size
    -0.06
     stigma
    -0.06
     亚洲
    -0.06
    POSITIVE LOGITS
     очи
    0.07
     Tampa
    0.07
     unintended
    0.06
     melodies
    0.06
     getApp
    0.06
     cevap
    0.06
     홈
    0.06
     retir
    0.06
     realtime
    0.06
     scenic
    0.06
    Act Density 0.000%

    No Known Activations