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

    Neuronpedia

    INDEX
    Explanations

    specific acronyms or technical terms often associated with various fields or disciplines

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

    parts of acronyms and specific names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     quelcon
    -0.56
     noastre
    -0.52
     quæ
    -0.52
    >
    -0.51
     userName
    -0.49
     quelconque
    -0.49
     aikana
    -0.49
    PRESA
    -0.48
    беріга
    -0.48
    óleo
    -0.48
    POSITIVE LOGITS
    tttt
    0.91
    ttt
    0.84
    tt
    0.82
    tet
    0.79
    t
    0.79
    at
    0.76
    zt
    0.74
    tert
    0.71
    tant
    0.70
    lt
    0.68
    Act Density 1.615%

    No Known Activations