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

    Neuronpedia

    INDEX
    Explanations

    acronym prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    apanicola
    0.29
    :"+
    0.28
    :“
    0.26
     sinful
    0.25
    <unused94>
    0.24
     nutritious
    0.24
     lumped
    0.24
     foolproof
    0.24
     acquies
    0.24
     mistrust
    0.24
    POSITIVE LOGITS
    ва
    0.25
    на
    0.25
    ↵↵
    0.23
    0.22
     S
    0.21
    ના
    0.21
    я
    0.21
    ॅ
    0.20
    app
    0.20
    боры
    0.20
    Act Density 0.184%

    No Known Activations