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

    Neuronpedia

    INDEX
    Explanations

    point

    np_max-act · gemini-2.0-flash

    discussions about machine intelligence and its potential threats to humanity.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     trimmed
    -0.06
    887
    -0.06
     traditional
    -0.06
     modern
    -0.06
     true
    -0.06
    .audio
    -0.06
     ASTM
    -0.06
     ساز
    -0.06
     attends
    -0.06
     cake
    -0.06
    POSITIVE LOGITS
    Nonce
    0.08
    \Migration
    0.08
     مستق
    0.08
    yntaxException
    0.08
    sizlik
    0.07
    και
    0.07
    γεν
    0.07
    nonce
    0.07
     вак
    0.07
    bla
    0.07
    Act Density 0.013%

    No Known Activations