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

    Neuronpedia

    INDEX
    Explanations

    session connection people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    azze
    0.38
    惚
    0.38
    Generalized
    0.38
    Ո
    0.38
    幄
    0.37
    ➰
    0.37
    igura
    0.36
    霧
    0.35
     دکھ
    0.35
    🔰
    0.35
    POSITIVE LOGITS
    äser
    0.40
     частини
    0.40
     брау
    0.38
     खिच
    0.38
    abled
    0.37
    켓
    0.37
     još
    0.37
     инвали
    0.37
    ítica
    0.36
    вов
    0.36
    Act Density 0.000%

    No Known Activations