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

    Neuronpedia

    INDEX
    Explanations

    measurements in kilometers and miles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Render
    0.37
    erede
    0.37
    ofsky
    0.37
    umn
    0.36
     neque
    0.36
     popularity
    0.34
    out
    0.34
     nowhere
    0.34
    erah
    0.34
     Roles
    0.33
    POSITIVE LOGITS
    ³)
    0.40
    °)
    0.38
    DOF
    0.38
     চক্ষ
    0.37
     erneut
    0.37
    ᛁ
    0.36
    emaking
    0.35
    িণী
    0.35
     señala
    0.34
    šnj
    0.34
    Act Density 0.029%

    No Known Activations