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

    Neuronpedia

    INDEX
    Explanations

    UTF-8 encoding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     outbreak
    0.87
     adherence
    0.84
     RHS
    0.80
     refraction
    0.79
     MATLAB
    0.78
     seemingly
    0.78
     fact
    0.78
     CBI
    0.76
     experiment
    0.76
     Python
    0.76
    POSITIVE LOGITS
     fielder
    1.07
    м
    1.06
    ૂ
    0.95
    й
    0.94
    чне
    0.93
    uner
    0.91
    чна
    0.90
    teau
    0.90
    at
    0.89
    ahir
    0.89
    Act Density 0.002%

    No Known Activations