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

    Neuronpedia

    INDEX
    Explanations

    first line

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rifer
    -0.08
    ligere
    -0.08
    precedented
    -0.08
    procedure
    -0.08
    finally
    -0.07
    xec
    -0.07
    Steph
    -0.07
    -pan
    -0.07
    ump
    -0.07
     Stall
    -0.07
    POSITIVE LOGITS
     থেকেই
    0.10
     خاک
    0.09
     उपाय
    0.08
     DRO
    0.08
     నుం�
    0.08
     Tij
    0.08
     כלי
    0.08
     priority
    0.08
    ဆုံး
    0.08
     अंग
    0.07
    Act Density 0.026%

    No Known Activations