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

    Neuronpedia

    INDEX
    Explanations

    Product descriptions

    np_max-act · gemini-2.0-flash

    The neuron spotlights formal metadata cues—particularly “Founded in [year],” and similar date‐and‐founding phrases.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    bcc
    -0.07
     recommends
    -0.06
     rapper
    -0.06
     Message
    -0.06
     innings
    -0.06
    .bz
    -0.06
    .messaging
    -0.06
     borrowed
    -0.06
    阅读
    -0.06
    (rd
    -0.06
    POSITIVE LOGITS
    �
    0.07
    )])
    0.07
     平方
    0.07
    밍
    0.06
    col
    0.06
    _exp
    0.06
     OnPropertyChanged
    0.06
     tum
    0.06
    구글상위
    0.06
    覆
    0.06
    Act Density 0.233%

    No Known Activations