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

    Neuronpedia

    INDEX
    Explanations

    reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Futures
    -0.07
    Isn
    -0.07
     Succ
    -0.06
     collected
    -0.06
     morality
    -0.06
     OMG
    -0.06
    URT
    -0.06
    ibly
    -0.06
     Mask
    -0.06
     عراق
    -0.06
    POSITIVE LOGITS
    -sided
    0.07
    सम
    0.07
    venile
    0.06
    薬
    0.06
    มข
    0.06
     zvuky
    0.06
     punished
    0.06
    Descending
    0.06
     bows
    0.06
     important
    0.06
    Act Density 0.165%

    No Known Activations