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

    Neuronpedia

    INDEX
    Explanations

    complex societal issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     irreversible
    -0.08
     undermines
    -0.07
     Forget
    -0.07
     Believe
    -0.07
    웨어
    -0.06
    ความร
    -0.06
    �
    -0.06
     believe
    -0.06
    -0.06
    Cause
    -0.06
    POSITIVE LOGITS
     pesos
    0.06
    .didReceiveMemoryWarning
    0.06
    欲
    0.06
    getRequest
    0.06
     предус
    0.06
    !/
    0.06
     wiki
    0.06
     uniq
    0.06
    pellier
    0.06
    /value
    0.06
    Act Density 0.168%

    No Known Activations