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

    Neuronpedia

    INDEX
    Explanations

    programming debugging

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    HL
    -0.07
    @store
    -0.07
     조사
    -0.07
    şk
    -0.06
     intoxicated
    -0.06
     Muslims
    -0.06
     elk
    -0.06
     propio
    -0.06
    벤
    -0.06
     ducks
    -0.06
    POSITIVE LOGITS
    654
    0.07
    NotNull
    0.07
    她们
    0.07
     LinearGradient
    0.07
    warn
    0.06
     philosophers
    0.06
    .parameters
    0.06
    	cfg
    0.06
    (move
    0.06
     resurrection
    0.06
    Act Density 0.002%

    No Known Activations