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
     nag
    -0.07
    .Queue
    -0.07
    !="
    -0.06
     Nasıl
    -0.06
     Bad
    -0.06
     đức
    -0.06
     pob
    -0.06
     بسی
    -0.06
     ave
    -0.06
     tối
    -0.06
    POSITIVE LOGITS
    ellation
    0.07
    102
    0.07
    767
    0.07
    787
    0.07
     day
    0.06
     styled
    0.06
     Training
    0.06
    ряд
    0.06
     xl
    0.06
    지원
    0.06
    Act Density 0.000%

    No Known Activations