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

    Neuronpedia

    INDEX
    Explanations

    links, markdown, code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pfl
    0.38
    -​
    0.38
     সো
    0.36
     horses
    0.35
    Acetyl
    0.35
     fi
    0.35
    Grunge
    0.35
     sarcom
    0.35
     Adirond
    0.35
    Packed
    0.35
    POSITIVE LOGITS
    М
    0.60
    У
    0.54
    П
    0.53
    А
    0.51
    Д
    0.50
    Б
    0.49
    Ма
    0.47
    К
    0.47
    Т
    0.46
    До
    0.46
    Act Density 0.175%

    No Known Activations