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

    Neuronpedia

    INDEX
    Explanations

    colors and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     scrapes
    0.45
    րա
    0.43
     abstractions
    0.38
     distortions
    0.38
     치
    0.37
     cytology
    0.37
     citizenry
    0.37
     countertop
    0.37
     modestly
    0.37
    ائر
    0.36
    POSITIVE LOGITS
    the
    0.69
     avere
    0.64
    is
    0.63
    in
    0.61
    é
    0.60
    在
    0.60
    ın
    0.59
    and
    0.58
    s
    0.58
     exemple
    0.57
    Act Density 0.000%

    No Known Activations