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

    Neuronpedia

    INDEX
    Explanations

    code declarations and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     salads
    0.44
     seterusnya
    0.40
    ®.
    0.40
    ச்சின்ன
    0.39
    暝
    0.38
     mahi
    0.38
    ahaan
    0.37
    ™.
    0.37
     bottlene
    0.36
    ⸨
    0.36
    POSITIVE LOGITS
    στηκε
    0.43
    ，
    0.41
    𝐆
    0.40
     T
    0.40
     ...)
    0.40
     И
    0.39
     М
    0.37
     especial
    0.37
     Т
    0.36
    ،
    0.36
    Act Density 0.007%

    No Known Activations