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

    Neuronpedia

    INDEX
    Explanations

    gentleman

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    簑
    0.36
     निय
    0.35
    even
    0.34
     conditionally
    0.34
     Quill
    0.34
     —
    0.34
     `{
    0.33
    Lack
    0.33
    lack
    0.33
    uje
    0.32
    POSITIVE LOGITS
    肦
    0.45
    ڎ
    0.41
     এইচডি
    0.37
    Fprintf
    0.37
     грошы
    0.37
    rological
    0.37
     crappy
    0.37
    0.37
    !='')
    0.37
     બ્
    0.37
    Act Density 0.000%

    No Known Activations