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

    Neuronpedia

    INDEX
    Explanations

    keys in data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     qubit
    0.35
    ELTS
    0.35
     cubic
    0.35
     set
    0.34
     व
    0.34
     যতদিন
    0.34
    |.
    0.33
     >=
    0.33
     converse
    0.33
     multitude
    0.33
    POSITIVE LOGITS
    another
    0.44
    ({});
    0.41
     Another
    0.40
     another
    0.38
    Another
    0.38
     മറ്റൊരു
    0.38
    另一个
    0.37
    ylle
    0.37
    োপাধ
    0.37
    バシー
    0.35
    Act Density 0.039%

    No Known Activations