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

    Neuronpedia

    INDEX
    Explanations

    Code/data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     humans
    -0.06
     **)
    -0.06
    ем
    -0.06
     burial
    -0.06
     رابطه
    -0.06
     shower
    -0.06
     withdrawal
    -0.06
    。。
    -0.06
     sip
    -0.06
     robotic
    -0.06
    POSITIVE LOGITS
     değiş
    0.07
    ques
    0.07
    Menus
    0.06
    _singleton
    0.06
    CSV
    0.06
    ecal
    0.06
     Mell
    0.06
    weis
    0.06
    inant
    0.06
    ermo
    0.06
    Act Density 0.000%

    No Known Activations