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

    Neuronpedia

    INDEX
    Explanations

    x

    np_max-act · gemini-2.0-flash

    The neuron activates on floating‐point number tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Мед
    -0.07
     oneself
    -0.07
     RAID
    -0.07
     Memo
    -0.06
    intern
    -0.06
    �
    -0.06
    Hang
    -0.06
    telefone
    -0.06
    IID
    -0.06
    لب
    -0.06
    POSITIVE LOGITS
     deltaX
    0.06
    _global
    0.06
    ziej
    0.06
    kových
    0.06
    bean
    0.06
     ступ
    0.06
    ximity
    0.06
    .jsx
    0.06
     тр
    0.06
     setw
    0.06
    Act Density 0.035%

    No Known Activations