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

    Neuronpedia

    INDEX
    Explanations

    state/federal relations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trafficking
    -0.07
     двиг
    -0.06
    rana
    -0.06
     içinde
    -0.06
    ลด
    -0.06
    (observer
    -0.06
    adow
    -0.06
     spotting
    -0.06
    �
    -0.06
    _PAYLOAD
    -0.05
    POSITIVE LOGITS
     len
    0.07
    sizei
    0.07
     hurdles
    0.07
     abdominal
    0.07
     intends
    0.07
    %A
    0.06
    GER
    0.06
     leadership
    0.06
    .LabelControl
    0.06
     Points
    0.06
    Act Density 0.109%

    No Known Activations