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

    Neuronpedia

    INDEX
    Explanations

    span

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =!
    -0.08
     נגד
    -0.08
    .job
    -0.08
     deter
    -0.08
    eter
    -0.07
    orris
    -0.07
     motivo
    -0.07
     bump
    -0.07
    _jobs
    -0.07
     forgetting
    -0.07
    POSITIVE LOGITS
    ㉹
    0.08
    -playing
    0.07
    -phase
    0.07
    량
    0.07
    span
    0.07
     Marketable
    0.07
    解决方案
    0.07
     Span
    0.07
    räg
    0.07
     pragma
    0.07
    Act Density 0.023%

    No Known Activations