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

    Neuronpedia

    INDEX
    Explanations

    general statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ST
    -0.08
     puss
    -0.07
    𬀪
    -0.07
     localVar
    -0.07
     inclination
    -0.07
     المعارضة
    -0.06
    忧虑
    -0.06
     pests
    -0.06
    intelligence
    -0.06
     bakeca
    -0.06
    POSITIVE LOGITS
     smoother
    0.07
    GameManager
    0.07
    �
    0.07
     remed
    0.07
    _slices
    0.07
    袄
    0.07
     ovarian
    0.07
     estudio
    0.07
    IMITER
    0.06
    userid
    0.06
    Act Density 0.075%

    No Known Activations