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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    descriptions related to post-apocalyptic settings and survival scenarios.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     consecutive
    -0.07
    (instruction
    -0.07
     EW
    -0.06
    Death
    -0.06
     unlimited
    -0.06
     Systems
    -0.06
     Blend
    -0.06
     первый
    -0.06
     leaks
    -0.06
     bác
    -0.06
    POSITIVE LOGITS
    ?',
    0.07
    -work
    0.06
     canada
    0.06
    -fin
    0.06
     görün
    0.06
    #__
    0.06
     mädchen
    0.06
    يني
    0.06
    ité
    0.06
    .summary
    0.06
    Act Density 0.051%

    No Known Activations