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

    Neuronpedia

    INDEX
    Explanations

    --no- prefix in commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ان
    2.08
    munition
    1.90
    an
    1.81
     fault
    1.80
    motiv
    1.77
    numeric
    1.76
    s
    1.75
    ים
    1.75
     ذه
    1.75
    প্রস
    1.74
    POSITIVE LOGITS
     ставить
    1.99
    ˒
    1.98
    otros
    1.96
     발생하는
    1.92
     flake
    1.90
     Auswirkungen
    1.87
     Abbiamo
    1.81
     Verwendung
    1.80
    üglich
    1.77
     Damit
    1.77
    Act Density 0.033%

    No Known Activations