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

    Neuronpedia

    INDEX
    Explanations

    simply

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _sensor
    -0.06
    /lo
    -0.06
    PRS
    -0.06
     Pend
    -0.06
     "@"
    -0.06
    ritten
    -0.06
    Boxes
    -0.06
    Sha
    -0.06
     admits
    -0.06
     lavish
    -0.06
    POSITIVE LOGITS
     underworld
    0.07
     демон
    0.07
    getOrElse
    0.07
    _SECOND
    0.06
    imestep
    0.06
     datové
    0.06
    .boot
    0.06
     χω
    0.06
     initialState
    0.06
    next
    0.06
    Act Density 0.000%

    No Known Activations