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

    Neuronpedia

    INDEX
    Explanations

    numbers 2, 120, 121, 125

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    કિસ્
    0.53
    ienka
    0.44
    ➀
    0.44
     morir
    0.43
    abhuto
    0.43
    ગાહી
    0.43
     ملتی
    0.42
    睐
    0.42
    iéndose
    0.42
     منسلک
    0.42
    POSITIVE LOGITS
    th
    0.58
     noon
    0.53
    и
    0.50
    _
    0.49
    AST
    0.49
    0.48
    J
    0.48
    O
    0.45
    시
    0.45
     apostles
    0.45
    Act Density 0.026%

    No Known Activations