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

    Neuronpedia

    INDEX
    Explanations

    model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    мимо
    0.35
    ricing
    0.32
    äte
    0.31
    isar
    0.30
     छह
    0.30
    നിര
    0.30
    över
    0.30
     நான்கு
    0.30
    intérieur
    0.29
    isasi
    0.29
    POSITIVE LOGITS
    g
    0.37
     sweetheart
    0.35
     aka
    0.34
     Bomb
    0.34
     answer
    0.33
     ANSWER
    0.31
    sm
    0.31
    sor
    0.31
    ラク
    0.31
     (.
    0.31
    Act Density 1.250%

    No Known Activations