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

    Neuronpedia

    INDEX
    Explanations

    Gaussian

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _LED
    -0.07
    -pres
    -0.06
    에는
    -0.06
    _sections
    -0.06
    евые
    -0.06
     entropy
    -0.06
    도록
    -0.06
     rew
    -0.06
    undaki
    -0.06
    moves
    -0.06
    POSITIVE LOGITS
     amusing
    0.07
     Gür
    0.07
    ocz
    0.06
     Herc
    0.06
     maize
    0.06
     Gaussian
    0.06
     те
    0.06
    _UUID
    0.06
    asia
    0.06
     Bash
    0.06
    Act Density 0.002%

    No Known Activations