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

    Neuronpedia

    INDEX
    Explanations

    that which

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Song
    -0.07
    sburg
    -0.07
     watcher
    -0.07
     능
    -0.07
    _Column
    -0.07
    Ind
    -0.07
    ;l
    -0.06
    rine
    -0.06
    éri
    -0.06
    Subject
    -0.06
    POSITIVE LOGITS
    dT
    0.08
     créd
    0.06
    theid
    0.06
     activism
    0.06
    uator
    0.06
    	code
    0.06
    žít
    0.06
     hacia
    0.06
    шила
    0.06
     pymongo
    0.06
    Act Density 0.040%

    No Known Activations