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

    Neuronpedia

    INDEX
    Explanations

    unavailability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    |x
    -0.07
    -d
    -0.06
    _multiple
    -0.06
    Qualifier
    -0.06
    त
    -0.06
     devoted
    -0.06
    resents
    -0.06
    amen
    -0.06
     hate
    -0.06
    芙
    -0.06
    POSITIVE LOGITS
    _SECRET
    0.06
     torino
    0.06
     professionnel
    0.06
    erty
    0.06
    (Collider
    0.06
     Bec
    0.06
     brawl
    0.06
    ihad
    0.06
     newPosition
    0.06
    arken
    0.06
    Act Density 0.011%

    No Known Activations