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

    Neuronpedia

    INDEX
    Explanations

    on the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     turns
    -0.07
     asks
    -0.06
     continues
    -0.06
     stuff
    -0.06
    　　　　　 　
    -0.06
     steal
    -0.06
     Week
    -0.06
    ran
    -0.06
     pager
    -0.05
     inflicted
    -0.05
    POSITIVE LOGITS
    League
    0.07
     Preis
    0.07
    larındaki
    0.07
    -height
    0.06
     METH
    0.06
    .Π
    0.06
    .green
    0.06
     colorWithRed
    0.06
    〔
    0.06
    Aliases
    0.06
    Act Density 0.018%

    No Known Activations