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

    Neuronpedia

    INDEX
    Explanations

    terms related to internet security vulnerabilities and hardware devices

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

    control systems, firmware, routers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    J
    -0.35
     Test
    -0.34
     j
    -0.34
     
    -0.33
     J
    -0.33
    b
    -0.33
    long
    -0.32
      
    -0.32
    machen
    -0.32
    I
    -0.32
    POSITIVE LOGITS
    ValueStyle
    0.73
    majánló
    0.69
     ſta
    0.68
     imagui
    0.65
    expandindo
    0.65
    enderror
    0.64
     laſſen
    0.63
    الحياه
    0.63
    writeFieldEnd
    0.62
     desmotivaciones
    0.61
    Act Density 0.034%

    No Known Activations