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

    Neuronpedia

    INDEX
    Explanations

    distinguish

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ॉप
    -0.07
     ($("#
    -0.07
     ngOnInit
    -0.07
     corpor
    -0.07
     carbs
    -0.06
    (getResources
    -0.06
     Corpor
    -0.06
     entered
    -0.06
     ora
    -0.06
    sql
    -0.06
    POSITIVE LOGITS
     distinguishing
    0.10
     distinguish
    0.08
     distinguished
    0.08
     distinction
    0.08
    ishes
    0.07
    Match
    0.07
    خته
    0.07
     distinctions
    0.07
    estro
    0.07
    vý
    0.07
    Act Density 0.006%

    No Known Activations