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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    unks
    -0.06
    ��
    -0.06
     hvad
    -0.06
     और
    -0.06
    mapper
    -0.06
    lfw
    -0.06
    ipmap
    -0.06
    низ
    -0.06
    mouseover
    -0.06
     Blackjack
    -0.06
    POSITIVE LOGITS
    _sm
    0.08
     WV
    0.07
    $result
    0.07
    /stdc
    0.07
     Vue
    0.06
     bols
    0.06
     phương
    0.06
    ,err
    0.06
     attenu
    0.06
    odon
    0.06
    Act Density 0.024%

    No Known Activations