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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating competition or contenders in various contexts

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

    candidate evaluation and disadvantages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pytania
    -0.35
    elemField
    -0.32
     pocz
    -0.31
    سمبر
    -0.29
     chronic
    -0.29
     physiology
    -0.29
    IntentFilter
    -0.29
     training
    -0.29
     góry
    -0.29
     warning
    -0.29
    POSITIVE LOGITS
     Candidate
    0.59
    Candidate
    0.58
    candidates
    0.58
     Candidates
    0.57
    Candidates
    0.56
    GOTREF
    0.55
    candidate
    0.55
    seemed
    0.54
    脚注の使い方
    0.54
     صوتيه
    0.54
    Act Density 0.456%

    No Known Activations