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

    Neuronpedia

    INDEX
    Explanations

    integer

    np_max-act · gemini-2.0-flash

    questions about mathematical operations, particularly roots and powers of numbers.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _WEIGHT
    -0.06
     Foo
    -0.06
    /script
    -0.06
    ases
    -0.06
     Exped
    -0.06
     portals
    -0.06
    (IS
    -0.06
    LP
    -0.06
     cig
    -0.06
     potion
    -0.05
    POSITIVE LOGITS
    recision
    0.07
    งช
    0.07
     виробництва
    0.06
    _planes
    0.06
    ором
    0.06
    intern
    0.06
     Georg
    0.06
     disposable
    0.06
    イズ
    0.06
    .cookies
    0.06
    Act Density 0.001%

    No Known Activations