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

    Neuronpedia

    INDEX
    Explanations

    phrases related to checking and validating connections, statuses, or conditions

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

    properly/correctly/adequately

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.59
    __(/*!
    -0.59
    makeText
    -0.42
    saraba
    -0.42
    CppCodeGen
    -0.40
    liferay
    -0.40
    oiseau
    -0.39
    endphp
    -0.39
    jaro
    -0.39
    Wrk
    -0.39
    POSITIVE LOGITS
     proper
    0.55
     appropriate
    0.53
     correct
    0.52
     adequate
    0.52
    正确的
    0.50
     properly
    0.48
    HomeAsUpEnabled
    0.46
     ComVisible
    0.44
     Adequate
    0.44
     corect
    0.44
    Act Density 0.041%

    No Known Activations