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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on floating‐point numeric tokens (decimal numbers) within the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ιστο
    -0.07
    	cancel
    -0.07
     newfound
    -0.07
    explained
    -0.06
     trap
    -0.06
     sharing
    -0.06
     духов
    -0.06
    吴
    -0.06
     ihtiy
    -0.06
     Oops
    -0.06
    POSITIVE LOGITS
    orig
    0.07
    .dtype
    0.06
    TYPE
    0.06
    ське
    0.06
     appropriate
    0.06
     SqlDataAdapter
    0.06
    arth
    0.06
    初始化
    0.06
     melhor
    0.06
     ComponentFixture
    0.06
    Act Density 0.024%

    No Known Activations