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

    Neuronpedia

    INDEX
    Explanations

    Speaking aloud

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     forces
    -0.06
    ロー
    -0.06
    Six
    -0.06
    Regarding
    -0.06
     flush
    -0.06
     frozen
    -0.06
    -seat
    -0.06
     force
    -0.06
    ẵ
    -0.06
     الخ
    -0.06
    POSITIVE LOGITS
     Gameplay
    0.06
    syscall
    0.06
    andatory
    0.06
    ěk
    0.06
     SHIPPING
    0.06
    CLUDED
    0.06
    ็
    0.06
    manda
    0.06
     embod
    0.06
    _PRODUCTS
    0.06
    Act Density 0.061%

    No Known Activations