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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -water
    -0.08
     <-
    -0.07
     Assistance
    -0.07
    -other
    -0.06
     labeling
    -0.06
    values
    -0.06
     flow
    -0.06
     lane
    -0.06
     Bez
    -0.06
    909
    -0.06
    POSITIVE LOGITS
    usaha
    0.06
     Giang
    0.06
    jeme
    0.06
     دوباره
    0.06
    εργ
    0.06
     cread
    0.06
     süt
    0.06
     troll
    0.06
    طاق
    0.06
     사람
    0.06
    Act Density 0.020%

    No Known Activations