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

    Neuronpedia

    INDEX
    Explanations

    links where available

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <h3>
    0.55
     Numer
    0.54
     numerically
    0.49
    Numer
    0.47
    numer
    0.45
    Numerical
    0.44
     numerical
    0.44
     Proble
    0.43
     problems
    0.42
     Numerical
    0.42
    POSITIVE LOGITS
    язви
    0.41
     يطلع
    0.40
    ipedia
    0.39
    ౌ
    0.39
    ₁.
    0.39
    ,":
    0.38
     отка
    0.38
    ᴊ
    0.38
     взгляд
    0.38
     করিতেছিল
    0.38
    Act Density 0.000%

    No Known Activations