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

    Neuronpedia

    INDEX
    Explanations

    most, many, majority

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⁻
    0.43
     '_'
    0.41
    ましょう
    0.40
    ।
    0.40
     ред
    0.39
    )['
    0.39
    組み
    0.38
    假設
    0.38
     Syd
    0.38
     Strat
    0.38
    POSITIVE LOGITS
     බොහෝ
    0.45
     meeste
    0.44
    nir
    0.44
     बहुतेक
    0.43
     대부분
    0.42
    തല്ല
    0.41
    並不
    0.41
     kebanyakan
    0.40
    ிருப்பது
    0.40
    oka
    0.39
    Act Density 0.000%

    No Known Activations