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

    Neuronpedia

    INDEX
    Explanations

    News reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bec
    -0.07
    board
    -0.07
    Bed
    -0.07
    tick
    -0.06
     digitally
    -0.06
     Legs
    -0.06
     xm
    -0.06
    заб
    -0.06
     Roller
    -0.06
     Worksheet
    -0.06
    POSITIVE LOGITS
     다음
    0.07
    ">'↵
    0.07
    593
    0.07
    _SID
    0.07
    RAIN
    0.06
    >'.
    0.06
    .Roles
    0.06
     consid
    0.06
     реги
    0.06
    >(*
    0.06
    Act Density 0.011%

    No Known Activations