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

    Neuronpedia

    INDEX
    Explanations

    words associated with humans or mankind, sometimes related to societal aspects, environment, or health.

    oai_token-act-pair · gemini-2.0-flash

    human

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     human
    -2.72
    human
    -2.36
     Human
    -2.28
    Human
    -2.27
     HUMAN
    -2.09
    HUMAN
    -1.91
     humain
    -1.73
     humans
    -1.72
     humano
    -1.71
     humanos
    -1.66
    POSITIVE LOGITS
    AndEndTag
    0.83
    oredCriteria
    0.81
     resourceCulture
    0.79
     Italijani
    0.71
    MENAFN
    0.71
    numerusform
    0.70
    HasForeignKey
    0.70
     onCreateView
    0.66
     rând
    0.65
    EndContext
    0.65
    Act Density 5.255%

    No Known Activations