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

    Neuronpedia

    INDEX
    Explanations

    college

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rtc
    -0.06
    inecraft
    -0.06
    阅读
    -0.06
    ().
    -0.06
    _own
    -0.06
    -----
    -0.06
    ersistence
    -0.06
    robot
    -0.06
    nl
    -0.06
     dies
    -0.06
    POSITIVE LOGITS
    čil
    0.07
     insure
    0.06
    教授
    0.06
     fren
    0.06
    disciplinary
    0.06
     electorate
    0.06
    <?=$
    0.06
     broadcast
    0.06
    чит
    0.06
     bylo
    0.06
    Act Density 0.224%

    No Known Activations