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

    Neuronpedia

    INDEX
    Explanations

    w

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bead
    -0.08
    ซื้อ
    -0.08
     remun
    -0.08
     probe
    -0.07
    uuu
    -0.07
    Grouping
    -0.07
    ті
    -0.07
    .Vol
    -0.07
     spanning
    -0.07
     families
    -0.07
    POSITIVE LOGITS
     cour
    0.09
     Shepherd
    0.08
     courte
    0.08
     предложение
    0.08
    isons
    0.08
     vag
    0.08
     marijuana
    0.08
    .typ
    0.08
     πρόγραμμα
    0.08
    قان
    0.07
    Act Density 0.001%

    No Known Activations