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

    Neuronpedia

    INDEX
    Explanations

    our

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    бут
    -0.06
    .source
    -0.06
    DoubleClick
    -0.06
    UNIX
    -0.06
    <!--↵
    -0.06
    NIL
    -0.06
    _ir
    -0.06
     дело
    -0.06
    OWL
    -0.06
    _sphere
    -0.06
    POSITIVE LOGITS
    ()});↵
    0.07
     jejím
    0.07
     dựng
    0.07
    ático
    0.07
     bakım
    0.06
     astounding
    0.06
    خواست
    0.06
    wed
    0.06
     Ans
    0.06
     climate
    0.06
    Act Density 0.013%

    No Known Activations