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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    date
    -0.07
     '.'
    -0.06
     Shore
    -0.06
    ('#
    -0.06
     Rhode
    -0.06
     ngắn
    -0.06
    _Page
    -0.06
     nejlepší
    -0.06
    -paper
    -0.06
     کود
    -0.06
    POSITIVE LOGITS
     Wifi
    0.07
    igy
    0.07
    aphrag
    0.07
    ῆς
    0.07
     mô
    0.06
     jit
    0.06
     �
    0.06
    .style
    0.06
    م
    0.06
    ُم
    0.06
    Act Density 0.019%

    No Known Activations