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

    Neuronpedia

    INDEX
    Explanations

    terms related to health risks and environmental threats

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

    protection from danger or harm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IUrlHelper
    -0.71
     defaultstate
    -0.66
    Personendaten
    -0.63
     للمعارف
    -0.60
    tinta
    -0.52
    MLLoader
    -0.51
     Meda
    -0.48
     pect
    -0.48
    onnaissance
    -0.47
     conqueror
    -0.46
    POSITIVE LOGITS
    phazard
    0.36
    LEGGI
    0.34
     <<<<<<<<<<<<<<
    0.33
     fallecido
    0.32
     znajdu
    0.32
     protegido
    0.32
     culturel
    0.31
    CardModule
    0.31
     ComVisible
    0.31
     hjæl
    0.30
    Act Density 0.136%

    No Known Activations