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

    Neuronpedia

    INDEX
    Explanations

    second-person perspective

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fucking
    -0.07
    	byte
    -0.06
     dusty
    -0.06
     chicks
    -0.06
    bis
    -0.06
    	distance
    -0.06
     glide
    -0.06
     että
    -0.06
     görün
    -0.06
     blasting
    -0.06
    POSITIVE LOGITS
     Repos
    0.08
    inar
    0.07
    _DRAW
    0.07
     Venez
    0.06
    .readFileSync
    0.06
     Believe
    0.06
     Fellow
    0.06
     검
    0.06
    /tab
    0.06
    ились
    0.06
    Act Density 0.027%

    No Known Activations