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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zeg
    -0.08
     গ্রহণ
    -0.08
     kailangan
    -0.08
     flex
    -0.07
     asked
    -0.07
    .flex
    -0.07
    petition
    -0.07
     behoeften
    -0.07
     open
    -0.07
    _REPEAT
    -0.07
    POSITIVE LOGITS
     Destroy
    0.08
     Viv
    0.08
     Loot
    0.08
     cheating
    0.07
    -small
    0.07
     चुकी
    0.07
     disastrous
    0.07
     royalties
    0.07
     spyware
    0.07
     poss
    0.07
    Act Density 0.027%

    No Known Activations