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

    Neuronpedia

    INDEX
    Explanations

    Everything

    np_max-act · gemini-2.0-flash

    informal conversational language related to storytelling and personal experiences.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Kid
    -0.07
     People
    -0.06
     ole
    -0.06
    .Unsupported
    -0.06
     upon
    -0.06
     inclined
    -0.06
    .Inject
    -0.06
     may
    -0.06
     might
    -0.06
    -or
    -0.06
    POSITIVE LOGITS
     everything
    0.14
     Everything
    0.10
    everything
    0.10
    Everything
    0.09
     everywhere
    0.08
    すべて
    0.07
    _filepath
    0.07
    THING
    0.07
    орт
    0.07
     Holland
    0.07
    Act Density 0.017%

    No Known Activations