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

    Neuronpedia

    INDEX
    Explanations

    ACL conference and related academic contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Công
    0.46
     YouTuber
    0.43
     Christmas
    0.40
     Halloween
    0.39
     Lobkowicz
    0.38
     Zoom
    0.38
     Vlog
    0.38
     Disney
    0.37
     Guinness
    0.37
     HIPAA
    0.37
    POSITIVE LOGITS
    RENGTH
    0.46
    ઞ
    0.40
    AIC
    0.40
    outfile
    0.39
    ACY
    0.39
     言っ
    0.39
    CLES
    0.39
    IAL
    0.37
    MetaData
    0.37
     සහ
    0.36
    Act Density 0.001%

    No Known Activations