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

    Neuronpedia

    INDEX
    Explanations

    sides, front, pulls over

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    it
    0.63
    től
    0.59
     branchNode
    0.59
    nelle
    0.56
     Editing
    0.56
    to
    0.55
    ından
    0.55
     Metadata
    0.55
     It
    0.54
    gerald
    0.53
    POSITIVE LOGITS
    0.64
    скім
    0.62
     causal
    0.59
    ке
    0.58
    な
    0.57
    цаў
    0.56
    𓏧
    0.56
     axi
    0.55
    𝔀
    0.55
     GAAP
    0.55
    Act Density 0.000%

    No Known Activations