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

    Neuronpedia

    INDEX
    Explanations

    edit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Placement
    -0.06
     lest
    -0.06
    _Product
    -0.06
    victim
    -0.06
    ，让
    -0.06
    aternity
    -0.06
    assert
    -0.06
    vehicles
    -0.06
    	trigger
    -0.06
     Мас
    -0.06
    POSITIVE LOGITS
    669
    0.06
    iała
    0.06
    USERNAME
    0.06
    rance
    0.06
    580
    0.06
    ham
    0.06
    	txt
    0.06
     insecure
    0.06
    permanent
    0.06
     atual
    0.06
    Act Density 0.000%

    No Known Activations