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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sockets
    -0.08
    -loader
    -0.06
    .PropTypes
    -0.06
     worthless
    -0.06
     Quad
    -0.06
    .vertical
    -0.06
     Property
    -0.06
     onData
    -0.06
    .record
    -0.06
    izr
    -0.06
    POSITIVE LOGITS
    _audit
    0.08
    (javax
    0.07
    imonials
    0.06
     █
    0.06
     CRM
    0.06
     gravid
    0.06
     subordinate
    0.06
     Avatar
    0.06
     دوست
    0.06
    ',

↵
    0.06
    Act Density 0.018%

    No Known Activations