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

    Neuronpedia

    INDEX
    Explanations

    focus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     LAT
    -0.07
    Teams
    -0.07
     Cups
    -0.06
    _nick
    -0.06
    Race
    -0.06
     blunt
    -0.06
    Portland
    -0.06
    {x
    -0.06
     pump
    -0.06
     Lamp
    -0.06
    POSITIVE LOGITS
     حرکت
    0.07
    isme
    0.07
     sahibi
    0.06
    ibernate
    0.06
     prejudice
    0.06
     fakat
    0.06
    フォ
    0.06
    .codehaus
    0.06
    vají
    0.06
    uide
    0.06
    Act Density 0.010%

    No Known Activations