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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    +x
    -0.08
     aseg
    -0.06
     saturation
    -0.06
    물을
    -0.06
     cent
    -0.06
    CLOSE
    -0.06
    -0.06
     adaptations
    -0.06
     ω
    -0.06
     temperatures
    -0.06
    POSITIVE LOGITS
    terra
    0.06
     NIGHT
    0.06
     studs
    0.06
    ंच
    0.06
    ัตถ
    0.06
     rospy
    0.06
    \Context
    0.06
     Bridge
    0.06
     APR
    0.06
     Donne
    0.06
    Act Density 0.104%

    No Known Activations