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

    Neuronpedia

    INDEX
    Explanations

    div class structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     style
    0.44
    wek
    0.40
     donde
    0.39
     sek
    0.37
    തര
    0.37
     xmlns
    0.36
    жда
    0.36
    публи
    0.35
     estilo
    0.34
     where
    0.34
    POSITIVE LOGITS
     Oracle
    0.48
    Oracle
    0.46
    Actions
    0.43
     Magdal
    0.42
    oracle
    0.42
     oracle
    0.38
    0.38
    Inputs
    0.37
    Gand
    0.37
     Gand
    0.37
    Act Density 0.001%

    No Known Activations