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

    Neuronpedia

    INDEX
    Explanations

    types and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Japanese
    0.48
     tekan
    0.48
    TextArea
    0.47
    Normalize
    0.47
    ToLower
    0.47
     इम्मेडिएटली
    0.44
    Andrew
    0.44
    Alo
    0.44
    Taiwan
    0.43
    ađ
    0.43
    POSITIVE LOGITS
     tipos
    0.46
     There
    0.46
    其
    0.46
    兩種
    0.45
     Modes
    0.44
    有两种
    0.41
     দুই
    0.40
     них
    0.39
     tipo
    0.39
     it
    0.39
    Act Density 0.004%

    No Known Activations