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

    Neuronpedia

    INDEX
    Explanations

    spokesman/woman

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    isan
    -0.07
     balık
    -0.07
    (pin
    -0.06
     quella
    -0.06
    loven
    -0.06
    ”),
    -0.06
    ิงหาคม
    -0.06
     Metro
    -0.06
    inish
    -0.06
    Inv
    -0.06
    POSITIVE LOGITS
    払
    0.06
     jmen
    0.06
     necess
    0.06
     assign
    0.06
    leyici
    0.06
    _false
    0.06
    ,s
    0.06
    _dr
    0.06
     ACCEPT
    0.06
    sci
    0.06
    Act Density 0.022%

    No Known Activations