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

    Neuronpedia

    INDEX
    Explanations

    Direction/Way

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    upport
    -0.07
    sd
    -0.07
    숙
    -0.07
    (){
↵
↵
    -0.06
    (schedule
    -0.06
     Goblin
    -0.06
     utterly
    -0.06
    _AP
    -0.06
     tư
    -0.06
    anagan
    -0.06
    POSITIVE LOGITS
    IOD
    0.06
     TRAIN
    0.06
     MODEL
    0.06
    -family
    0.06
    aje
    0.06
    izacao
    0.06
    arella
    0.06
     gris
    0.06
    fill
    0.06
     Georg
    0.06
    Act Density 0.009%

    No Known Activations