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

    Neuronpedia

    INDEX
    Explanations

    Random strings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Payment
    -0.08
     президент
    -0.07
    torch
    -0.07
    rPid
    -0.07
    passwd
    -0.06
    COMMAND
    -0.06
    _PLAY
    -0.06
    RESSION
    -0.06
    rails
    -0.06
     Apartment
    -0.06
    POSITIVE LOGITS
     �
    0.06
    .asInstanceOf
    0.06
    788
    0.06
    �
    0.06
    ého
    0.06
     nostra
    0.06
    　ゝ
    0.06
     authorize
    0.06
     зокрема
    0.06
     enh
    0.06
    Act Density 0.013%

    No Known Activations