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

    Neuronpedia

    INDEX
    Explanations

    combinations or represent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     geschlossen
    0.40
     ప్రమా
    0.39
    ᱛ
    0.39
    ள்
    0.39
    тый
    0.38
    lç
    0.38
     gigantic
    0.38
    ای
    0.37
    layer
    0.37
     colossal
    0.37
    POSITIVE LOGITS
     (“
    0.42
     (‘
    0.40
     (’
    0.39
    钳
    0.38
    嶠
    0.38
     Discussions
    0.37
     cups
    0.37
     Novels
    0.37
    炤
    0.37
    AppSettings
    0.36
    Act Density 0.001%

    No Known Activations