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

    Neuronpedia

    INDEX
    Explanations

    social climate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fermion
    0.38
    烦
    0.36
     reparto
    0.35
     shenanigans
    0.35
     gaze
    0.35
     }],
    0.35
    тение
    0.34
     gy
    0.33
    ές
    0.33
     mesmer
    0.33
    POSITIVE LOGITS
    ifton
    0.49
     AFI
    0.45
    bf
    0.45
     പിന്തുണ
    0.42
     başka
    0.39
    \%.
    0.39
    Otro
    0.39
     လူ
    0.38
     Otro
    0.38
     sant
    0.38
    Act Density 0.000%

    No Known Activations