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

    Neuronpedia

    INDEX
    Explanations

    world

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .spaceBetween
    -0.07
     校
    -0.06
     sacrifice
    -0.06
     Iowa
    -0.06
    gay
    -0.06
     Rio
    -0.06
     Анг
    -0.06
    桂
    -0.06
     коман
    -0.06
     高
    -0.06
    POSITIVE LOGITS
    .DisplayMember
    0.07
    mentation
    0.07
     onFocus
    0.07
     grop
    0.07
    -demo
    0.06
     γρα
    0.06
    REL
    0.06
     /************************************************************************
    0.06
     Encrypt
    0.06
     покры
    0.06
    Act Density 0.034%

    No Known Activations