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

    Neuronpedia

    INDEX
    Explanations

    th

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     victim
    -0.07
    REEN
    -0.07
    าฟ
    -0.07
     будет
    -0.06
    充
    -0.06
    Correct
    -0.06
    Production
    -0.06
    	error
    -0.06
    upt
    -0.06
    birthdate
    -0.06
    POSITIVE LOGITS
     schematic
    0.07
     真
    0.06
     форми
    0.06
     Tinder
    0.06
    .userInteractionEnabled
    0.06
    mî
    0.06
    JSGlobal
    0.06
     परम
    0.05
     totalPages
    0.05
     wenig
    0.05
    Act Density 0.012%

    No Known Activations