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

    Neuronpedia

    INDEX
    Explanations

    say "p" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trillion
    -0.08
     relacion
    -0.08
    svg
    -0.07
    .De
    -0.07
    _ok
    -0.07
    错误
    -0.07
     alo
    -0.07
    联通
    -0.07
     списка
    -0.07
    夭
    -0.07
    POSITIVE LOGITS
     boasts
    0.07
    Focused
    0.07
     makers
    0.07
     stark
    0.07
     Bold
    0.07
     DSP
    0.07
     poetic
    0.07
     Hatch
    0.06
    JOB
    0.06
    [text
    0.06
    Act Density 0.003%

    No Known Activations