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

    Neuronpedia

    INDEX
    Explanations

    research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PEED
    -0.08
     discharge
    -0.07
     strike
    -0.07
     Canary
    -0.07
     ดาว
    -0.07
     HID
    -0.06
     male
    -0.06
     follow
    -0.06
    될
    -0.06
     Challenge
    -0.06
    POSITIVE LOGITS
    missible
    0.07
    吐
    0.06
    _sparse
    0.06
    инов
    0.06
    여
    0.06
     idiot
    0.06
     helm
    0.06
    ثمان
    0.06
    Jobs
    0.06
    прав
    0.06
    Act Density 0.010%

    No Known Activations