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

    Neuronpedia

    INDEX
    Explanations

    professionals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    बर
    -0.08
     marital
    -0.07
     statute
    -0.07
    ゆ
    -0.07
     boxes
    -0.06
     Immigration
    -0.06
     fueled
    -0.06
    utt
    -0.06
    caffold
    -0.06
     waterproof
    -0.06
    POSITIVE LOGITS
    _signature
    0.07
    ='',↵
    0.07
    _modify
    0.06
    	as
    0.06
    不
    0.06
    Simply
    0.06
     servis
    0.06
    utures
    0.06
    187
    0.06
    .firstName
    0.06
    Act Density 0.014%

    No Known Activations