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

    Neuronpedia

    INDEX
    Explanations

    args

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     môi
    -0.07
    ीटर
    -0.07
     Muhammed
    -0.06
    SEG
    -0.06
     gsl
    -0.06
     mỗi
    -0.06
    ioxide
    -0.06
    (team
    -0.06
    律宾
    -0.06
     mop
    -0.06
    POSITIVE LOGITS
     randomness
    0.06
    なし
    0.06
    belief
    0.06
    args
    0.06
     Forest
    0.06
    $name
    0.06
    Ford
    0.06
     contracted
    0.06
     primal
    0.06
    -average
    0.06
    Act Density 0.001%

    No Known Activations