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

    Neuronpedia

    INDEX
    Explanations

    comment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     recourse
    -0.07
    ωνα
    -0.07
     penal
    -0.07
     plate
    -0.06
     Num
    -0.06
    decision
    -0.06
     berries
    -0.06
    .Tab
    -0.06
     stat
    -0.06
     pace
    -0.06
    POSITIVE LOGITS
    _Msp
    0.07
     predic
    0.07
    .super
    0.06
     Cairo
    0.06
     ↑
    0.06
    _ag
    0.06
    _slave
    0.06
    道路
    0.06
    }</
    0.06
    ResponseBody
    0.06
    Act Density 0.006%

    No Known Activations