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

    Neuronpedia

    INDEX
    Explanations

    exterior/external

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ""){↵
    -0.08
     Strat
    -0.08
     transplantation
    -0.08
     pilot
    -0.07
     infusion
    -0.07
     breeder
    -0.07
    -0.07
    Pilot
    -0.07
     Pilot
    -0.07
     urgently
    -0.07
    POSITIVE LOGITS
     beträgt
    0.10
     отриц
    0.09
    Angle
    0.09
     Acción
    0.08
    .Action
    0.08
     negativo
    0.08
     составляет
    0.08
    _angle
    0.08
     Excess
    0.08
     Degree
    0.08
    Act Density 0.005%
    No Known Activations