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

    Neuronpedia

    INDEX
    Explanations

    operated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     targeting
    -0.07
     batching
    -0.07
    enburg
    -0.07
     kes
    -0.07
    ail
    -0.07
     swaps
    -0.06
     reliant
    -0.06
    ab
    -0.06
    @Web
    -0.06
    ancellable
    -0.06
    POSITIVE LOGITS
    Якщо
    0.07
    _secondary
    0.07
     والتي
    0.06
     энерг
    0.06
    \Events
    0.06
    θερ
    0.06
     tends
    0.06
     ;-
    0.06
    TA
    0.06
    事務
    0.06
    Act Density 0.004%

    No Known Activations