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

    Neuronpedia

    INDEX
    Explanations

    ugal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     *</
    -0.07
     Murphy
    -0.06
    816
    -0.06
    ेव
    -0.06
     محمود
    -0.06
     NEVER
    -0.06
     snap
    -0.06
    416
    -0.06
    Enlarge
    -0.06
    _NR
    -0.06
    POSITIVE LOGITS
     Award
    0.07
     Inv
    0.06
    (statearr
    0.06
    uchi
    0.06
    outcome
    0.06
     上涨
    0.06
    ALLOW
    0.06
    chalk
    0.06
     restless
    0.06
     tends
    0.06
    Act Density 0.044%

    No Known Activations