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

    Neuronpedia

    INDEX
    Explanations

    addresses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     entrusted
    -0.08
    によ
    -0.08
     om
    -0.07
     lends
    -0.07
    kate
    -0.07
    (Q
    -0.07
    mapper
    -0.06
    兵
    -0.06
    Nx
    -0.06
     irrig
    -0.06
    POSITIVE LOGITS
    !;↵
    0.07
     сред
    0.07
    vern
    0.06
    umo
    0.06
     labelText
    0.06
     bekl
    0.06
     ')'
    0.06
    ále
    0.06
    $rows
    0.06
     nuovo
    0.06
    Act Density 0.005%

    No Known Activations