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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    holding
    -0.07
    iqu
    -0.06
    transforms
    -0.06
    hou
    -0.06
     propriet
    -0.06
    ipmap
    -0.06
    二十
    -0.06
     inout
    -0.06
     Госп
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    (previous
    0.07
     ☆
    0.07
     produces
    0.06
     accessibility
    0.06
     Chips
    0.06
    (Property
    0.06
    Calendar
    0.06
    _Def
    0.06
     Canal
    0.06
    Investigators
    0.06
    Act Density 0.012%

    No Known Activations