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

    Neuronpedia

    INDEX
    Explanations

    descriptions of situations/emotions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Donovan
    -0.07
     درست
    -0.07
    ProgressBar
    -0.06
     Razor
    -0.06
     Spread
    -0.06
     Wouldn
    -0.06
    吨
    -0.06
    lý
    -0.06
    Comparer
    -0.06
     Couldn
    -0.06
    POSITIVE LOGITS
     strategies
    0.06
    pagesize
    0.06
     fol
    0.06
     projected
    0.06
    thes
    0.06
     disreg
    0.06
     implications
    0.06
    _sha
    0.06
    _U
    0.06
    								↵
    0.06
    Act Density 0.083%

    No Known Activations