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

    Neuronpedia

    INDEX
    Explanations

    ser

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     regrett
    -0.07
    Am
    -0.07
    �
    -0.07
    -0.07
     ಗ
    -0.07
    mat
    -0.07
    wé
    -0.07
     trag
    -0.07
     ho
    -0.07
     fo
    -0.07
    POSITIVE LOGITS
     carefree
    0.08
     Consumer
    0.08
    ệp
    0.08
     ان
    0.08
     assaults
    0.08
     awesome
    0.07
     consumer
    0.07
     fique
    0.07
     confidence
    0.07
    ////////////////////////////////////////////////////////////////////
    0.07
    Act Density 0.000%
    No Known Activations