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

    Neuronpedia

    INDEX
    Explanations

    conversations

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of custom assistant or AI persona names (e.g. “NAME_1”, “Social Bot”) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    BV
    -0.07
     الأخرى
    -0.07
     Plasma
    -0.07
    Dirs
    -0.07
    hesion
    -0.06
    ös
    -0.06
    Rot
    -0.06
    DMA
    -0.06
    eve
    -0.06
    edla
    -0.06
    POSITIVE LOGITS
     �
    0.07
     floatValue
    0.07
    .Cascade
    0.07
     خش
    0.07
    <bits
    0.07
    �
    0.06
    rací
    0.06
    Segoe
    0.06
     か
    0.06
     vòng
    0.06
    Act Density 0.021%

    No Known Activations