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

    Neuronpedia

    INDEX
    Explanations

    file names or identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wèi
    0.42
    Weak
    0.41
    Dealing
    0.41
     playerCount
    0.41
    Tip
    0.40
    context
    0.40
    Err
    0.40
    Info
    0.40
    Promise
    0.40
    Error
    0.40
    POSITIVE LOGITS
    ழிப்பு
    0.46
    abases
    0.44
     strips
    0.44
     និង
    0.43
     nila
    0.43
     রাখেন
    0.42
    চ্ছিলেন
    0.42
     rusak
    0.42
     luta
    0.42
     mexicano
    0.41
    Act Density 1.500%

    No Known Activations