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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Е
    -0.07
    answered
    -0.07
    /angular
    -0.07
     towers
    -0.07
     mileage
    -0.07
    ۱
    -0.07
     preocup
    -0.07
    iations
    -0.07
    _particle
    -0.07
    idenav
    -0.06
    POSITIVE LOGITS
    abase
    0.08
     activist
    0.07
    、、
    0.07
    CHAT
    0.06
    /Sh
    0.06
     cupboard
    0.06
    _DL
    0.06
     nez
    0.06
     sustained
    0.06
    ớt
    0.06
    Act Density 0.000%

    No Known Activations