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

    Neuronpedia

    INDEX
    Explanations

    restricting and rejecting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _character
    -0.08
    Comments
    -0.07
    (column
    -0.06
    .xxx
    -0.06
     VIS
    -0.06
     coupon
    -0.06
    (cond
    -0.06
     каш
    -0.06
    Simply
    -0.06
    وه
    -0.06
    POSITIVE LOGITS
     tedav
    0.07
     itu
    0.07
     är
    0.07
    lında
    0.07
     ăn
    0.07
     Furious
    0.07
     FRA
    0.07
     misunderstood
    0.06
     Sadd
    0.06
    xAC
    0.06
    Act Density 0.007%

    No Known Activations