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

    Neuronpedia

    INDEX
    Explanations

    shoulders back

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     العد
    0.39
    ୟ
    0.38
    禎
    0.38
     AcOH
    0.38
    ரசுக்
    0.37
     सुर
    0.37
     Kaltura
    0.37
    CuO
    0.37
    फ्ते
    0.37
    عد
    0.37
    POSITIVE LOGITS
     plat
    0.38
     olímp
    0.37
     Moore
    0.37
     Stad
    0.36
    irim
    0.36
     staircase
    0.36
    럇
    0.36
     hierarchical
    0.36
     სიმ
    0.36
     Plat
    0.36
    Act Density 0.001%

    No Known Activations