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

    Neuronpedia

    INDEX
    Explanations

    term

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    volve
    -0.07
     morceaux
    -0.07
     fenô
    -0.07
    ,password
    -0.07
     ongeveer
    -0.07
    ,<
    -0.07
    ങ്ങളിലും
    -0.07
    سب
    -0.07
     frozen
    -0.07
     hippoc
    -0.07
    POSITIVE LOGITS
     grupa
    0.09
     ఆధ
    0.09
     насколько
    0.08
     Acrylic
    0.08
     Saints
    0.08
    асці
    0.08
     BOM
    0.08
     kul
    0.08
     наск
    0.07
    MMMM
    0.07
    Act Density 0.001%

    No Known Activations