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

    Neuronpedia

    INDEX
    Explanations

    on trips and adventures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thresholds
    0.48
     workflows
    0.47
     benchmarks
    0.46
     kth
    0.44
     pianos
    0.44
    DWARF
    0.44
     wellbeing
    0.42
    MADE
    0.42
     florals
    0.42
     straws
    0.42
    POSITIVE LOGITS
    ovať
    0.52
    ificar
    0.49
     excursion
    0.47
     tournée
    0.46
     நீண்ட
    0.46
     recorrer
    0.45
     excursions
    0.44
    diendo
    0.44
    ょ
    0.44
    इसलिए
    0.44
    Act Density 0.011%

    No Known Activations