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

    Neuronpedia

    INDEX
    Explanations

    async Task

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Duties
    0.40
    Contracts
    0.39
     Letter
    0.38
     Guardians
    0.37
     implications
    0.37
    outines
    0.37
     duties
    0.36
     Rounds
    0.36
    DOT
    0.36
     guard
    0.34
    POSITIVE LOGITS
    广
    0.47
     वाइड
    0.46
     Wide
    0.44
    Wide
    0.42
    ußer
    0.41
    𝚏
    0.40
    TISE
    0.40
     출력
    0.39
    copyWith
    0.39
    𝗷
    0.39
    Act Density 0.000%

    No Known Activations