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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     میان
    -0.06
    ANGUAGE
    -0.06
     chỗ
    -0.06
     xung
    -0.06
    bí
    -0.06
     انگلیسی
    -0.06
    堆
    -0.06
     अलग
    -0.06
    oga
    -0.05
    بالإنجليزية
    -0.05
    POSITIVE LOGITS
    (prev
    0.07
     finite
    0.07
     meeting
    0.06
    (red
    0.06
    ooky
    0.06
     fearing
    0.06
    >L
    0.06
     triangle
    0.06
    .param
    0.06
     konz
    0.06
    Act Density 0.017%

    No Known Activations