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

    Neuronpedia

    INDEX
    Explanations

    say "illness"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    𝓷
    -0.08
    ılan
    -0.07
    쑻
    -0.07
     этого
    -0.07
    uelle
    -0.07
    ("")↵
    -0.07
    étr
    -0.07
    ('')↵
    -0.07
     ta
    -0.07
    (bit
    -0.07
    POSITIVE LOGITS
    ;;;;
    0.08
    真是太
    0.07
    рад
    0.07
    髋
    0.07
    .scalar
    0.07
    😎
    0.07
     ejaculation
    0.07
     wParam
    0.07
     Radeon
    0.07
    쟝
    0.07
    Act Density 0.030%

    No Known Activations