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

    Neuronpedia

    INDEX
    Explanations

    geometric shapes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ordre
    0.84
     dis
    0.82
     triangle
    0.81
     square
    0.81
     order
    0.80
     chaf
    0.78
     in
    0.77
    square
    0.77
    ôté
    0.76
     إليه
    0.74
    POSITIVE LOGITS
    otted
    0.80
     имел
    0.78
     DH
    0.78
     должна
    0.75
     BH
    0.73
    SSH
    0.73
     ል
    0.73
    VOC
    0.73
    aujourd
    0.72
     היא
    0.72
    Act Density 0.000%

    No Known Activations