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

    Neuronpedia

    INDEX
    Explanations

    +

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Elim
    -0.08
     Yük
    -0.07
    -n
    -0.07
    _emlrt
    -0.07
     dzi
    -0.06
     Shawn
    -0.06
    wner
    -0.06
     freezes
    -0.06
    Owner
    -0.06
    _radius
    -0.06
    POSITIVE LOGITS
     remained
    0.07
     storia
    0.06
     Highland
    0.06
     implanted
    0.06
     personalities
    0.06
    +
    0.06
     +
    0.06
    curring
    0.06
    About
    0.06
     Virgin
    0.06
    Act Density 0.032%

    No Known Activations