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

    Neuronpedia

    INDEX
    Explanations

    substitution in equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tips
    -0.09
     Tips
    -0.08
     pagh
    -0.08
     Tas
    -0.08
    زع
    -0.07
    .swap
    -0.07
    rie
    -0.07
     kéo
    -0.07
     metá
    -0.07
    angepicker
    -0.07
    POSITIVE LOGITS
    Membership
    0.08
    coordinates
    0.08
     plugged
    0.08
     membership
    0.08
    Coordinates
    0.08
    _members
    0.07
     ingres
    0.07
    -members
    0.07
     coorden
    0.07
     Coordinates
    0.07
    Act Density 0.055%

    No Known Activations