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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     année
    -0.07
    scrollTop
    -0.07
     düzenlenen
    -0.07
    .concat
    -0.07
    -feira
    -0.07
     amnesty
    -0.07
     bacon
    -0.07
     consumption
    -0.07
    鹋
    -0.07
    око
    -0.07
    POSITIVE LOGITS
     [{
    0.07
     MMO
    0.07
    EQUAL
    0.07
    สม
    0.07
    福特
    0.06
    (glm
    0.06
     xcb
    0.06
     cảm
    0.06
    您同意
    0.06
     ({
    0.06
    Act Density 0.022%

    No Known Activations