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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Clients
    -0.07
    _ta
    -0.07
     opponent
    -0.07
    district
    -0.07
    _Default
    -0.06
     demanding
    -0.06
    templ
    -0.06
     dealer
    -0.06
    ốt
    -0.06
    anker
    -0.06
    POSITIVE LOGITS
     suiv
    0.07
    .Ad
    0.07
    /tasks
    0.07
     ''.
    0.07
     estava
    0.07
     fputs
    0.06
     fuera
    0.06
     Scient
    0.06
     voir
    0.06
     поль
    0.06
    Act Density 0.237%

    No Known Activations