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

    Neuronpedia

    INDEX
    Explanations

    code examples and outputs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ЛИ
    0.40
    ±
    0.40
    enhuma
    0.39
    ณะ
    0.39
     言っ
    0.37
     insidious
    0.37
    ಮನ
    0.36
    ENN
    0.36
    Loaded
    0.35
    verses
    0.35
    POSITIVE LOGITS
     junio
    0.45
    ्योपै
    0.45
     divisor
    0.44
     Binding
    0.42
     giugno
    0.40
    飪
    0.40
     történ
    0.39
    防护
    0.39
     IntVar
    0.39
     săn
    0.38
    Act Density 0.021%

    No Known Activations