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

    Neuronpedia

    INDEX
    Explanations

    Pain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     расстоя
    -0.09
     distances
    -0.08
     Meister
    -0.08
    raft
    -0.08
     Lein
    -0.07
     hurdles
    -0.07
    generator
    -0.07
     दूरी
    -0.07
     Leap
    -0.07
     dài
    -0.07
    POSITIVE LOGITS
     suspected
    0.16
     suspe
    0.15
     sospe
    0.15
     suspicion
    0.15
     подоз
    0.14
     suspicious
    0.14
     সন্দ
    0.12
     suspects
    0.12
    疑
    0.12
     suspect
    0.12
    Act Density 0.038%

    No Known Activations