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

    Neuronpedia

    INDEX
    Explanations

    Code, programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     societies
    -0.07
     hers
    -0.07
     marketers
    -0.07
    إن
    -0.07
    -int
    -0.06
    _tem
    -0.06
     EN
    -0.06
     Connecting
    -0.06
    (IO
    -0.06
    .Str
    -0.06
    POSITIVE LOGITS
     Hearth
    0.07
    洗
    0.07
    uintptr
    0.06
    haft
    0.06
     pleaded
    0.06
    _vlan
    0.06
    慧
    0.06
     lite
    0.06
     rootReducer
    0.06
    Donald
    0.06
    Act Density 0.011%

    No Known Activations