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

    Neuronpedia

    INDEX
    Explanations

    risk posture, feature representations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Manifest
    0.38
     Landmark
    0.38
     Charleston
    0.38
     টালি
    0.37
     Alpes
    0.37
     appropriate
    0.37
    Mountains
    0.37
     Sigma
    0.36
     directed
    0.36
     XML
    0.36
    POSITIVE LOGITS
    assapi
    0.45
    դ
    0.45
    DELETE
    0.42
     asignar
    0.41
    剃
    0.39
     Predicting
    0.39
    ッティング
    0.38
    Detective
    0.38
     tetanus
    0.38
    smiley
    0.38
    Act Density 0.002%

    No Known Activations