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

    Neuronpedia

    INDEX
    Explanations

    SIP and related acronyms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ឯ
    0.44
    ponent
    0.41
    zeuge
    0.38
    స్ట్రీ
    0.38
    Meetings
    0.38
     వర్
    0.38
    waża
    0.37
    ologne
    0.36
     ejected
    0.36
    ทุก
    0.36
    POSITIVE LOGITS
     sip
    0.70
     Sip
    0.59
     SIP
    0.55
    sip
    0.55
     sipping
    0.52
    SIP
    0.50
     ==============
    0.41
     viola
    0.37
     सुप
    0.36
     push
    0.35
    Act Density 0.003%

    No Known Activations