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

    Neuronpedia

    INDEX
    Explanations

    say "developer tool"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SIZE
    -0.06
    qué
    -0.06
     unfit
    -0.06
    adj
    -0.06
    _usec
    -0.06
     Harrison
    -0.06
     січ
    -0.06
    ैप
    -0.06
     deprecated
    -0.06
    Copy
    -0.06
    POSITIVE LOGITS
     disrupted
    0.06
    ltr
    0.06
     روست
    0.06
    روت
    0.06
     suốt
    0.06
     whale
    0.06
     Grat
    0.06
     eventual
    0.06
    _cal
    0.06
    Designer
    0.06
    Act Density 0.020%

    No Known Activations