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

    Neuronpedia

    INDEX
    Explanations

    various

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     เด
    -0.07
     Fame
    -0.07
    Stand
    -0.07
     included
    -0.06
     прес
    -0.06
     overpower
    -0.06
    timeout
    -0.06
     Hardcore
    -0.06
     Serie
    -0.06
    powered
    -0.06
    POSITIVE LOGITS
     various
    0.11
    Various
    0.08
     Various
    0.08
    Several
    0.07
    -www
    0.06
    Mgr
    0.06
     Respir
    0.06
     verschied
    0.06
    окон
    0.06
    혜
    0.06
    Act Density 0.038%

    No Known Activations