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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Window
    -0.07
    然而
    -0.07
     �
    -0.07
     din
    -0.07
    jf
    -0.07
     juni
    -0.07
     Frank
    -0.06
    $sub
    -0.06
     �
    -0.06
     аль
    -0.06
    POSITIVE LOGITS
    (dtype
    0.06
     systems
    0.06
    -security
    0.06
     část
    0.06
    ownik
    0.06
    String
    0.06
    tparam
    0.06
    _SEARCH
    0.06
    絵
    0.06
    #ac
    0.06
    Act Density 0.000%

    No Known Activations