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

    Neuronpedia

    INDEX
    Explanations

    then

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .gl
    -0.07
     Gio
    -0.07
     tossing
    -0.07
     hops
    -0.06
     sweeping
    -0.06
    riad
    -0.06
     predatory
    -0.06
    圧
    -0.06
     Aerospace
    -0.06
    Crop
    -0.06
    POSITIVE LOGITS
     Then
    0.11
    Then
    0.10
     then
    0.07
     dann
    0.07
     href
    0.07
    Ин
    0.07
     (~
    0.07
     �
    0.06
     insurg
    0.06
     後
    0.06
    Act Density 0.034%

    No Known Activations