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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fs
    -0.07
    esar
    -0.07
     \@
    -0.07
     Functor
    -0.06
     md
    -0.06
    <pre
    -0.06
    :\"
    -0.06
    'll
    -0.06
     buddies
    -0.06
     Cowboys
    -0.06
    POSITIVE LOGITS
    мець
    0.07
     VE
    0.06
     define
    0.06
     habe
    0.06
     recommand
    0.06
     PED
    0.06
    arez
    0.06
     scientifically
    0.06
     pan
    0.06
     メ
    0.06
    Act Density 0.050%

    No Known Activations