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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to mechanical or structural issues in objects

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

    Punctuation followed by specific words

    np_acts-logits-general · gemini-2.0-flash

    preventing problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    期刊论文
    -0.53
     decision
    -0.48
     συμ
    -0.48
     Ausgang
    -0.46
     öz
    -0.46
    iteiten
    -0.45
     reservado
    -0.45
    Sklici
    -0.44
    decision
    -0.44
     escol
    -0.43
    POSITIVE LOGITS
     removing
    0.77
     excessive
    0.74
     Prevents
    0.73
     water
    0.71
     prevents
    0.71
    Removing
    0.71
     overheating
    0.71
     excess
    0.71
     prevent
    0.70
    Preventing
    0.69
    Act Density 0.539%

    No Known Activations