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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tip
    -0.07
    tec
    -0.07
     stringify
    -0.07
     Gos
    -0.06
     Toe
    -0.06
    agar
    -0.06
     tot
    -0.06
     tip
    -0.06
    _learn
    -0.06
     libertin
    -0.06
    POSITIVE LOGITS
    érience
    0.07
    LONG
    0.07
     هتل
    0.07
     apply
    0.07
    lang
    0.07
     ευ
    0.06
     TRANS
    0.06
    арів
    0.06
     Seriously
    0.06
    -analytics
    0.06
    Act Density 0.035%

    No Known Activations