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

    Neuronpedia

    INDEX
    Explanations

    measurable scientific properties

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Akt
    -0.06
     overwhelming
    -0.06
     classroom
    -0.06
     corrective
    -0.06
    Once
    -0.06
     swe
    -0.06
     inhibitor
    -0.06
    _overlap
    -0.06
     Conn
    -0.06
    _UP
    -0.06
    POSITIVE LOGITS
    мот
    0.07
    INSTANCE
    0.07
    stocks
    0.06
    urb
    0.06
     mediums
    0.06
    uib
    0.06
     tome
    0.06
    metatable
    0.06
     Directory
    0.06
    achusetts
    0.06
    Act Density 0.058%

    No Known Activations