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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (strcmp
    -0.07
    north
    -0.07
    /plain
    -0.07
     north
    -0.07
     kino
    -0.07
     unfinished
    -0.07
     south
    -0.06
    _kernel
    -0.06
    dem
    -0.06
     bless
    -0.06
    POSITIVE LOGITS
     Coupons
    0.07
     गत
    0.06
    cantidad
    0.06
     asp
    0.06
    addElement
    0.06
    NSDate
    0.06
     Nr
    0.06
     Expl
    0.06
     adequ
    0.06
     공고
    0.06
    Act Density 0.025%

    No Known Activations