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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Test
    -0.08
     dieser
    -0.06
    -copy
    -0.06
    .Normalize
    -0.06
    Culture
    -0.06
     perfectly
    -0.06
    ...)↵↵
    -0.06
     Between
    -0.06
     between
    -0.06
     suicide
    -0.06
    POSITIVE LOGITS
     ferr
    0.07
    Als
    0.07
    歯
    0.06
     organizace
    0.06
    scar
    0.06
     bildir
    0.06
     zakáz
    0.06
     Alan
    0.06
    ٣
    0.06
    constraints
    0.06
    Act Density 0.006%

    No Known Activations