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

    Neuronpedia

    INDEX
    Explanations

    7 Cups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uro
    0.39
    sig
    0.38
     banc
    0.38
     ¬
    0.38
    processable
    0.37
     firmware
    0.37
     fenced
    0.36
     bank
    0.35
     pork
    0.35
     Bank
    0.35
    POSITIVE LOGITS
     necessitate
    0.40
    䒨
    0.40
    athin
    0.39
     প্রয়োজন
    0.39
     hated
    0.38
    ChessBot
    0.38
     ಸಾಮಾನ್ಯ
    0.37
     costing
    0.37
     ала
    0.37
     resented
    0.37
    Act Density 0.000%

    No Known Activations