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

    Neuronpedia

    INDEX
    Explanations

    mentions of protein fragments and their characteristics in medical or scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Difficulty, complexity, or rarity

    np_acts-logits-general · gemini-2.0-flash

    hidden or complex

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    carril
    -0.51
    tement
    -0.50
    átek
    -0.49
    atchewan
    -0.49
     tut
    -0.48
    SPATH
    -0.47
     Sing
    -0.47
    itattu
    -0.47
    Šaltiniai
    -0.46
    stridium
    -0.46
    POSITIVE LOGITS
     cryptic
    0.85
     obfusc
    0.84
     obscured
    0.83
     obscurity
    0.83
     confusing
    0.81
     obscure
    0.81
     hidden
    0.79
     opaque
    0.75
    隐藏
    0.74
     unmarked
    0.74
    Act Density 0.626%

    No Known Activations