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

    Neuronpedia

    INDEX
    Explanations

    code punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.47
    Data
    0.44
    Bs
    0.42
    E
    0.41
    M
    0.41
    ጨማሪ
    0.40
     প্ৰ
    0.40
    AL
    0.40
    ATI
    0.40
    ForThe
    0.40
    POSITIVE LOGITS
    т
    0.50
    ↵
    0.46
    "
    0.44
    ي
    0.42
    “
    0.42
     umano
    0.42
    ে
    0.40
    น
    0.40
    𝒚
    0.40
    或是
    0.39
    Act Density 2.606%

    No Known Activations