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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     acre
    -0.10
    /OR
    -0.09
    905
    -0.09
    eli
    -0.09
    ely
    -0.09
     Butler
    -0.09
    oeff
    -0.09
     Fitz
    -0.08
    /native
    -0.08
    929
    -0.08
    POSITIVE LOGITS
    -long
    0.21
    ì§ľ
    0.20
    -olds
    0.19
    -old
    0.18
    -wide
    0.15
    etre
    0.15
    elsius
    0.13
    /-
    0.12
    ers
    0.12
    sworth
    0.12
    Act Density 0.091%

    No Known Activations