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

    Neuronpedia

    INDEX
    Explanations

    Guinea

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Confederacy
    -0.91
     auffi
    -0.82
     Learner
    -0.79
    EndInit
    -0.79
     guineas
    -0.79
     ―――――
    -0.78
    saraba
    -0.77
     fubject
    -0.77
     ſtand
    -0.77
     ſte
    -0.77
    POSITIVE LOGITS
     (
    0.52
     C
    0.51
     I
    0.46
     köz
    0.46
     X
    0.45
     V
    0.44
     
    0.44
     or
    0.43
     kø
    0.42
     P
    0.42
    Act Density 0.054%

    No Known Activations