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

    Neuronpedia

    INDEX
    Explanations

    links

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     notice
    -0.08
     escape
    -0.07
    vanized
    -0.07
    .focus
    -0.07
    涄
    -0.07
     DIG
    -0.07
    .docs
    -0.07
    뵨
    -0.07
    _HISTORY
    -0.07
     recruiting
    -0.07
    POSITIVE LOGITS
    uds
    0.07
    истем
    0.07
     urinary
    0.07
     Overs
    0.07
    During
    0.07
    ubern
    0.07
    аниз
    0.07
    棉
    0.07
     pady
    0.07
    建军
    0.07
    Act Density 0.003%

    No Known Activations