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

    Neuronpedia

    INDEX
    Explanations

    into

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LOC
    -0.07
    광
    -0.07
    Sync
    -0.06
     TAG
    -0.06
     تغ
    -0.06
    bel
    -0.06
    BP
    -0.06
    ear
    -0.06
     CPI
    -0.06
    (act
    -0.06
    POSITIVE LOGITS
     entren
    0.06
     personn
    0.06
    verification
    0.06
    _mentions
    0.06
     фунда
    0.06
    _SECONDS
    0.06
     Федераль
    0.06
    _roles
    0.06
    Thirty
    0.06
    -render
    0.06
    Act Density 0.027%

    No Known Activations