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

    Neuronpedia

    INDEX
    Explanations

    explaining an offering/product

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    frast
    0.41
    etera
    0.40
     출연
    0.40
     inferences
    0.39
     clinging
    0.39
     vivid
    0.39
    ávez
    0.38
    herjee
    0.38
     নানা
    0.38
    पाला
    0.38
    POSITIVE LOGITS
     Ger
    0.41
     Tomas
    0.39
     Caldwell
    0.39
     Guid
    0.38
     Eva
    0.37
     Ad
    0.36
     Grav
    0.36
     initial
    0.35
    初始
    0.35
    ੁੱ
    0.35
    Act Density 0.001%

    No Known Activations