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

    Neuronpedia

    INDEX
    Explanations

    oregano, LastError, skepticism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nibb
    0.49
    ن
    0.48
     gener
    0.45
     dragons
    0.44
    vans
    0.42
     Algebras
    0.42
     matern
    0.42
    sql
    0.42
     rychle
    0.42
     rapidamente
    0.41
    POSITIVE LOGITS
    EVEN
    0.52
    方針
    0.48
     किसको
    0.46
    ()=>{
    0.46
     музей
    0.46
     حتی
    0.44
     बरत
    0.44
    が変わ
    0.42
    efined
    0.42
    atoire
    0.42
    Act Density 0.004%

    No Known Activations