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

    Neuronpedia

    INDEX
    Explanations

    avoid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     coursework
    -0.07
    IMER
    -0.07
    稞
    -0.07
     cœur
    -0.07
     fashionable
    -0.07
     Faker
    -0.07
     Kota
    -0.07
    .food
    -0.07
     Rico
    -0.07
    เทคโน
    -0.07
    POSITIVE LOGITS
    	ts
    0.08
    差距
    0.08
    bay
    0.07
     conspir
    0.07
    nx
    0.07
     эфф
    0.07
     instantly
    0.07
     projects
    0.07
     actually
    0.07
    .operations
    0.07
    Act Density 0.038%

    No Known Activations