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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pony
    -0.06
     condom
    -0.06
    _subtype
    -0.06
     {/*
    -0.06
     Deep
    -0.06
    xy
    -0.06
    .mainloop
    -0.06
    ีข
    -0.06
    irror
    -0.06
    fee
    -0.06
    POSITIVE LOGITS
     Cheers
    0.07
    ]↵↵
    0.07
     chic
    0.06
     Approximately
    0.06
     유
    0.06
     invaluable
    0.06
     pokemon
    0.06
     leave
    0.06
    nums
    0.06
    ublice
    0.06
    Act Density 0.000%

    No Known Activations