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

    Neuronpedia

    INDEX
    Explanations

    see

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     haciendo
    -0.06
    西省
    -0.06
    _Total
    -0.06
    기준
    -0.06
     arrogant
    -0.06
     wandered
    -0.05
     smelled
    -0.05
    aq
    -0.05
    884
    -0.05
    164
    -0.05
    POSITIVE LOGITS
    ivement
    0.07
     대부분
    0.07
    triangle
    0.06
     दव
    0.06
    ranges
    0.06
     Houses
    0.06
     �
    0.06
    καν
    0.06
    
    0.06
    reements
    0.06
    Act Density 0.025%

    No Known Activations