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

    Neuronpedia

    INDEX
    Explanations

    "because you have"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vanes
    0.36
    為
    0.35
     steric
    0.33
     utensils
    0.33
    ून्य
    0.31
     sil
    0.31
     identification
    0.31
     CLOS
    0.30
     odor
    0.30
     保
    0.30
    POSITIVE LOGITS
    ߋ
    0.45
    ⲟ
    0.43
    isetas
    0.42
    ⅼ
    0.39
    blogger
    0.37
    blog
    0.37
    ᧐
    0.36
    credibly
    0.34
    arette
    0.34
     Blog
    0.34
    Act Density 0.002%

    No Known Activations