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

    Neuronpedia

    INDEX
    Explanations

    impute

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     suite
    -0.07
    OPER
    -0.06
    adan
    -0.06
     accel
    -0.06
     Lep
    -0.06
    .borrow
    -0.06
     attack
    -0.06
    stractions
    -0.06
    Attack
    -0.06
     Attack
    -0.06
    POSITIVE LOGITS
     ώρα
    0.07
    objectManager
    0.07
     　 　 　 　
    0.06
     Sylvia
    0.06
    �
    0.06
    -years
    0.06
    ‌شوند
    0.06
    λω
    0.06
    -blue
    0.06
    analyze
    0.06
    Act Density 0.003%

    No Known Activations