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

    Neuronpedia

    INDEX
    Explanations

    methods and measurement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    passwd
    -0.07
    LOUR
    -0.06
     viewHolder
    -0.06
    Off
    -0.06
    �i
    -0.06
    ï
    -0.06
     नर
    -0.06
     scalability
    -0.06
    _Manager
    -0.06
     liberty
    -0.06
    POSITIVE LOGITS
     social
    0.07
     PCS
    0.07
    ulled
    0.06
     문의
    0.06
    _ONLY
    0.06
    Wenn
    0.06
    -alone
    0.06
     '[
    0.06
    cmb
    0.06
    social
    0.06
    Act Density 0.161%

    No Known Activations