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

    Neuronpedia

    INDEX
    Explanations

    only

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     originating
    -0.07
     (\<
    -0.07
     spilled
    -0.06
    posed
    -0.06
     otherButtonTitles
    -0.06
    AINED
    -0.06
    uria
    -0.06
    claims
    -0.06
     mapped
    -0.06
    Ln
    -0.06
    POSITIVE LOGITS
    اضی
    0.06
    imag
    0.06
    κι
    0.06
    ово
    0.06
    egot
    0.06
    -coordinate
    0.06
     añ
    0.06
     možná
    0.06
    ροφορίες
    0.06
    dda
    0.06
    Act Density 0.000%

    No Known Activations