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

    Neuronpedia

    INDEX
    Explanations

    history sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    is
    0.45
    م
    0.41
    umlahan
    0.40
    𒉰
    0.39
    𝐿
    0.38
    ions
    0.37
     कोणते
    0.37
     چیزی
    0.35
    ivité
    0.34
    晦
    0.34
    POSITIVE LOGITS
     സംഭവ
    0.40
     président
    0.37
     Vigo
    0.35
    సాగ
    0.35
     klub
    0.35
     lainnya
    0.34
     intensa
    0.34
     approfond
    0.34
     klubu
    0.34
     podczas
    0.34
    Act Density 0.004%

    No Known Activations