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

    Neuronpedia

    INDEX
    Explanations

    Code involving x,y

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     resurrection
    -0.07
    ukes
    -0.07
     GNU
    -0.06
    urrection
    -0.06
    INU
    -0.06
    _ALERT
    -0.06
     dol
    -0.06
    	float
    -0.06
     embed
    -0.06
     advant
    -0.06
    POSITIVE LOGITS
    States
    0.07
     مبار
    0.07
    aspers
    0.07
    @n
    0.06
     transmitting
    0.06
     caution
    0.06
     )↵↵↵
    0.06
     habil
    0.06
    (numpy
    0.06
    ,it
    0.06
    Act Density 0.083%

    No Known Activations