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

    Neuronpedia

    INDEX
    Explanations

    ld

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _rho
    -0.07
    .CASCADE
    -0.07
     beaten
    -0.07
     stability
    -0.07
    (par
    -0.07
     disjoint
    -0.07
     adultos
    -0.06
     Level
    -0.06
     walkers
    -0.06
    _winner
    -0.06
    POSITIVE LOGITS
    ld
    0.08
    d
    0.07
    hd
    0.07
    struction
    0.07
     Bulldogs
    0.07
    boxing
    0.06
    PrototypeOf
    0.06
    ckett
    0.06
    _mD
    0.06
    LError
    0.06
    Act Density 0.002%

    No Known Activations