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

    Neuronpedia

    INDEX
    Explanations

    participants

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fry
    -0.08
     Busty
    -0.08
    :SetPoint
    -0.07
    .Setup
    -0.07
    dry
    -0.07
    หลวง
    -0.07
    swift
    -0.07
    .bindingNavigator
    -0.07
    \web
    -0.07
     zdję
    -0.07
    POSITIVE LOGITS
    participant
    0.07
    (panel
    0.07
     participants
    0.07
     représent
    0.06
    これまで
    0.06
    価
    0.06
    lesc
    0.06
    솬
    0.06
    icipant
    0.06
     athlete
    0.06
    Act Density 0.008%

    No Known Activations