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

    Neuronpedia

    INDEX
    Explanations

    Excerpts of longer texts

    np_max-act · gemini-2.0-flash

    This neuron detects the end-of-header marker that introduces assistant-generated text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    �
    -0.07
    ρει
    -0.07
    time
    -0.07
     typ
    -0.07
    *);↵↵
    -0.06
    problem
    -0.06
    udent
    -0.06
    める
    -0.06
     Talk
    -0.06
    bearer
    -0.06
    POSITIVE LOGITS
    ("$
    0.07
     поврежд
    0.07
     πιο
    0.06
    Predicate
    0.06
    (':
    0.06
    OLON
    0.06
     ضربه
    0.06
     identifier
    0.06
    ("---
    0.06
    ære
    0.06
    Act Density 0.010%

    No Known Activations