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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _LO
    -0.07
     "_
    -0.07
    िं
    -0.06
     yanlış
    -0.06
    _"
    -0.06
     estates
    -0.06
     Kč
    -0.06
     worms
    -0.06
    法院
    -0.06
     две
    -0.06
    POSITIVE LOGITS
    گو
    0.07
     really
    0.07
     Independent
    0.07
    ellow
    0.07
    inement
    0.07
     purified
    0.06
    acic
    0.06
     localStorage
    0.06
    loomberg
    0.06
    Extended
    0.06
    Act Density 0.028%

    No Known Activations