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

    Neuronpedia

    INDEX
    Explanations

    case

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     _)
    -0.06
    clf
    -0.06
     بده
    -0.06
    Manchester
    -0.06
    殺
    -0.06
    Что
    -0.06
     gastr
    -0.05
    788
    -0.05
    ively
    -0.05
     PAR
    -0.05
    POSITIVE LOGITS
     klid
    0.07
    ĩnh
    0.07
     qi
    0.07
     Vanity
    0.07
     �
    0.07
    Twig
    0.07
    (li
    0.07
    (mid
    0.07
    .getValue
    0.07
    ahun
    0.07
    Act Density 0.007%

    No Known Activations