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

    Neuronpedia

    INDEX
    Explanations

    babysitters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     heroine
    -0.07
    regnum
    -0.07
    (rawValue
    -0.07
     Huang
    -0.07
     Royale
    -0.06
     Macedonia
    -0.06
     Philippe
    -0.06
    worm
    -0.06
     mailing
    -0.06
     Compound
    -0.06
    POSITIVE LOGITS
     реш
    0.06
    	register
    0.06
    423
    0.06
    優
    0.06
     TOM
    0.06
    τωση
    0.06
    *=
    0.06
    700
    0.06
    (clicked
    0.06
    Cons
    0.06
    Act Density 0.004%

    No Known Activations