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

    Neuronpedia

    INDEX
    Explanations

    ]

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    phis
    -0.06
    τήσεις
    -0.06
     территории
    -0.06
    리를
    -0.06
    _categorical
    -0.06
    =os
    -0.06
     dem
    -0.06
     noodles
    -0.06
    setVisible
    -0.06
     Gameplay
    -0.06
    POSITIVE LOGITS
     Bloody
    0.07
    Improved
    0.07
    (bits
    0.06
     spotting
    0.06
    .chars
    0.06
    的问题
    0.06
     proper
    0.06
    .hwp
    0.06
    quiry
    0.06
     Flip
    0.06
    Act Density 0.000%

    No Known Activations