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

    Neuronpedia

    INDEX
    Explanations

    how to respond

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     GAAP
    0.51
     SGD
    0.49
     Deane
    0.49
    랄
    0.48
     fraction
    0.47
     catalogue
    0.46
     Cayman
    0.45
     Gerald
    0.45
     pept
    0.44
     chromatic
    0.43
    POSITIVE LOGITS
    P
    0.55
     abril
    0.54
    也
    0.53
     agosto
    0.52
    Ak
    0.52
     altri
    0.51
    Mult
    0.50
     أيضا
    0.50
     fate
    0.49
    مه
    0.49
    Act Density 0.000%

    No Known Activations