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

    Neuronpedia

    INDEX
    Explanations

    column names, schema analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mun
    0.41
     mun
    0.41
     Argy
    0.39
     насколько
    0.38
    mun
    0.38
    Tok
    0.37
    plexity
    0.36
    欲
    0.36
    otypes
    0.36
     Embedding
    0.36
    POSITIVE LOGITS
     Class
    0.38
    看起來
    0.38
    人員
    0.38
     Directly
    0.38
    明確
    0.38
     peric
    0.38
    াতি
    0.38
     Pursuant
    0.37
    Clearly
    0.37
     trimmed
    0.37
    Act Density 0.000%

    No Known Activations