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

    Neuronpedia

    INDEX
    Explanations

    defining parameters for language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ibilität
    0.44
     chất
    0.42
    یی
    0.42
     feared
    0.42
    uğu
    0.42
    ристо
    0.41
     quảng
    0.40
    ми
    0.40
    éditeur
    0.39
    வத
    0.39
    POSITIVE LOGITS
    $\--
    0.61
     motivo
    0.52
     Second
    0.49
     defini
    0.48
    getString
    0.47
    ()-
    0.46
     Defining
    0.46
    ة
    0.46
    redient
    0.45
     insp
    0.45
    Act Density 0.001%

    No Known Activations