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

    Neuronpedia

    INDEX
    Explanations

    2 or 3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .want
    -0.07
     lasting
    -0.07
    μές
    -0.07
    海道
    -0.06
     collapsed
    -0.06
     Onun
    -0.06
    (constants
    -0.06
    _inf
    -0.06
     병
    -0.06
    orary
    -0.06
    POSITIVE LOGITS
    ็นว
    0.06
     UIBar
    0.06
     hızla
    0.06
     announcements
    0.06
     domác
    0.06
     stát
    0.05
     balık
    0.05
     Truck
    0.05
    _USED
    0.05
    Looper
    0.05
    Act Density 0.006%

    No Known Activations