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

    Neuronpedia

    INDEX
    Explanations

    business phrases and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    schol
    0.38
     ViewGroup
    0.38
     scholarship
    0.37
    histo
    0.36
    rug
    0.36
    crime
    0.36
    ケー
    0.36
    scholar
    0.36
    co
    0.36
    granted
    0.36
    POSITIVE LOGITS
    ăș
    0.44
    attan
    0.42
    ↓↓
    0.42
     Fid
    0.41
     arranger
    0.40
    ಷ್ಟು
    0.40
     categorize
    0.39
     Vladim
    0.39
    Proced
    0.38
     verwendeten
    0.38
    Act Density 0.001%

    No Known Activations