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

    Neuronpedia

    INDEX
    Explanations

    inside

    np_max-act · gemini-2.0-flash

    The neuron detects causative “bring out the inner X” phrases that describe drawing out someone’s internal state.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     unread
    -0.07
     acceleration
    -0.07
     resets
    -0.06
    /utils
    -0.06
    .NewReader
    -0.06
     таблиц
    -0.06
     retaliation
    -0.06
     návrh
    -0.06
     screenplay
    -0.06
     provid
    -0.06
    POSITIVE LOGITS
    End
    0.08
    SW
    0.07
    IBILITY
    0.07
    issen
    0.07
    istical
    0.07
    �
    0.06
    بار
    0.06
     splitter
    0.06
    ancellation
    0.06
     ง
    0.06
    Act Density 0.017%

    No Known Activations