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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Рег
    -0.08
     Klein
    -0.07
     Bry
    -0.07
     Brady
    -0.07
     Address
    -0.06
    blink
    -0.06
     pag
    -0.06
     strt
    -0.06
    ifo
    -0.06
     Fol
    -0.06
    POSITIVE LOGITS
     jeopardy
    0.07
     evac
    0.06
    �
    0.06
    شمالی
    0.06
     indices
    0.06
     Armen
    0.06
    ="${
    0.06
     vự
    0.06
     juni
    0.06
     sau
    0.06
    Act Density 0.107%

    No Known Activations