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

    Neuronpedia

    INDEX
    Explanations

    Code/data structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     isEqual
    -0.07
    922
    -0.07
     trapping
    -0.06
    	long
    -0.06
    来た
    -0.06
     night
    -0.06
     aerial
    -0.06
     resizable
    -0.06
    _RT
    -0.06
    754
    -0.06
    POSITIVE LOGITS
     delights
    0.06
     thematic
    0.06
    战斗
    0.06
     αγα
    0.06
    .No
    0.06
     وما
    0.06
    (map
    0.06
     Ε
    0.06
    Cheers
    0.06
     провод
    0.06
    Act Density 0.094%

    No Known Activations