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

    Neuronpedia

    INDEX
    Explanations

    find

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cada
    -0.07
    تمتع
    -0.07
     Lager
    -0.07
    ᠦ
    -0.07
     RF
    -0.06
    ڑ
    -0.06
     Principal
    -0.06
     להש
    -0.06
     SEC
    -0.06
     Tang
    -0.06
    POSITIVE LOGITS
    ||(
    0.07
    腨
    0.07
     ocur
    0.07
     napisał
    0.07
    指挥部
    0.07
    _confirm
    0.06
    ################################################################
    0.06
     porque
    0.06
    response
    0.06
     paragraphs
    0.06
    Act Density 0.005%

    No Known Activations