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

    Neuronpedia

    INDEX
    Explanations

    Hypothetical scenarios

    np_max-act · gemini-2.0-flash

    the neuron detects hypothetical or conditional prompts that begin with phrases like "If you..." (questions asking what would happen or what someone would do).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     Νο
    -0.07
     Dup
    -0.07
     crates
    -0.07
    ULA
    -0.06
    ウス
    -0.06
    (ctrl
    -0.06
    جب
    -0.06
     corruption
    -0.06
    xs
    -0.06
    Transport
    -0.06
    POSITIVE LOGITS
    stdexcept
    0.07
     Yorkshire
    0.07
     MagicMock
    0.06
     точ
    0.06
     UIAlert
    0.06
     Jain
    0.06
     JSGlobal
    0.06
     acquaint
    0.06
    θούν
    0.06
    (shape
    0.06
    Act Density 0.037%

    No Known Activations