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

    Neuronpedia

    INDEX
    Explanations

    Although

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ViewGroup
    -0.07
    kinson
    -0.07
     encourages
    -0.06
     Folk
    -0.06
     Sistema
    -0.06
    .Linked
    -0.06
     McCarthy
    -0.06
     Energ
    -0.06
     Sixth
    -0.06
    igroup
    -0.06
    POSITIVE LOGITS
    *↵
    0.07
     titre
    0.07
    Weapons
    0.06
    uisse
    0.06
    ี,
    0.06
    *',
    0.06
     qualité
    0.06
    "].
    0.06
    obutton
    0.06
     올라
    0.06
    Act Density 0.017%

    No Known Activations