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

    Neuronpedia

    INDEX
    Explanations

    by and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ாளையம்
    0.42
     ن
    0.39
     haver
    0.37
     victorias
    0.36
     nariz
    0.36
    हाबाद
    0.36
     Mancini
    0.35
    ਸੀ
    0.34
    මුත්
    0.34
     Bereits
    0.34
    POSITIVE LOGITS
    Bye
    0.48
     bye
    0.45
    ennem
    0.44
     위에
    0.42
    を表
    0.41
    bent
    0.39
    ಕ್ಕೆ
    0.39
    0.39
    Württemberg
    0.39
    ennom
    0.39
    Act Density 0.000%

    No Known Activations