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

    Neuronpedia

    INDEX
    Explanations

    mell

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	f
    -0.07
    _unlock
    -0.07
    .reward
    -0.07
    figcaption
    -0.07
     Dragon
    -0.06
    @",
    -0.06
    واز
    -0.06
    .erb
    -0.06
    "d
    -0.06
     occured
    -0.06
    POSITIVE LOGITS
     impressions
    0.07
     spans
    0.07
     sor
    0.06
    !
    0.06
    /-
    0.06
     nastav
    0.06
    HEY
    0.06
     Syndrome
    0.06
     azalt
    0.06
    0
    0.06
    Act Density 0.003%

    No Known Activations