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

    Neuronpedia

    INDEX
    Explanations

    end of sentence or phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     spree
    0.63
     webinars
    0.61
     conquests
    0.61
     ໃນ
    0.59
    咱們
    0.58
    <unused57>
    0.58
     possui
    0.58
     Radcliffe
    0.58
    росло
    0.58
    راتكم
    0.57
    POSITIVE LOGITS
    false
    0.61
    He
    0.59
    It
    0.57
    Then
    0.57
    基于
    0.57
    @
    0.54
     "
    0.54
     (
    0.53
    he
    0.52
    exponential
    0.52
    Act Density 0.192%

    No Known Activations