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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to technology and structure in various contexts

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

    high

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    󠁴
    -0.44
    )*/
    -0.42
     relaxes
    -0.41
     novices
    -0.41
    Autoritní
    -0.41
    뀜
    -0.40
     */;
    -0.39
     shells
    -0.39
    identité
    -0.39
    permitAll
    -0.39
    POSITIVE LOGITS
     high
    1.54
    high
    1.41
    High
    1.38
     High
    1.34
    HIGH
    1.24
     HIGH
    1.20
     tinggi
    1.16
     yüksek
    1.14
    高
    1.11
     higher
    1.03
    Act Density 0.176%

    No Known Activations