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

    Neuronpedia

    INDEX
    Explanations

    grouped bycategorized bysubdivided into

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Y
    0.55
    El
    0.52
    ю
    0.49
    Adresse
    0.49
    J
    0.45
    E
    0.44
    Am
    0.43
    It
    0.43
    Ch
    0.43
    H
    0.42
    POSITIVE LOGITS
     classifications
    1.17
     categories
    1.12
     categorized
    1.11
    三种
    1.07
     categor
    1.02
     three
    1.00
    分为
    1.00
     categorize
    0.98
    分為
    0.98
     types
    0.98
    Act Density 0.105%

    No Known Activations