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

    Neuronpedia

    INDEX
    Explanations

    references to various types of water or solutions in a scientific context

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

    distilled water

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Roskov
    -0.73
    UrlResolution
    -0.70
    sizeCache
    -0.57
     @"/
    -0.55
    Hochspringen
    -0.55
    uxxxx
    -0.54
    Autoritní
    -0.53
    :✨
    -0.53
    utnik
    -0.52
     Offisielt
    -0.51
    POSITIVE LOGITS
    tijden
    0.38
     personeel
    0.35
     woorden
    0.34
    verhältnisse
    0.32
     verhalen
    0.31
     Beteiligung
    0.31
    ANGAN
    0.28
    あく
    0.28
    angan
    0.28
     kræ
    0.27
    Act Density 0.003%

    No Known Activations