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

    Neuronpedia

    INDEX
    Explanations

    factors influence each other

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zwięks
    0.54
     használ
    0.52
     gratis
    0.51
     gratuitement
    0.49
     overkill
    0.48
     effiz
    0.47
     verified
    0.46
     empfohlen
    0.46
     збіль
    0.46
     lossless
    0.46
    POSITIVE LOGITS
     influences
    0.91
     влияет
    0.80
    influence
    0.80
     influenced
    0.79
     influence
    0.79
     влия
    0.78
     influencia
    0.76
     beeinfl
    0.74
     повлия
    0.74
     влияния
    0.73
    Act Density 0.146%

    No Known Activations