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

    Neuronpedia

    INDEX
    Explanations

    themes of survival and crime in narratives

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

    safety rail

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.52
    Personensuche
    -0.47
    tagext
    -0.44
     дописавши
    -0.44
    MONG
    -0.43
    цездатний
    -0.43
     udało
    -0.42
    WebMethod
    -0.42
    łas
    -0.42
     mxArray
    -0.42
    POSITIVE LOGITS
    iläum
    0.42
    piecze
    0.41
    renza
    0.40
    ceğine
    0.39
    الإنجليزية
    0.39
    cepti
    0.38
    巯
    0.36
    ocio
    0.36
    salud
    0.35
    DeviceInfo
    0.35
    Act Density 0.110%

    No Known Activations