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

    Neuronpedia

    INDEX
    Explanations

    aid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     зда
    -0.08
     wła
    -0.07
     HVAC
    -0.07
     SHOW
    -0.07
     Infant
    -0.06
    ivil
    -0.06
    abet
    -0.06
     hind
    -0.06
     fec
    -0.06
     swallow
    -0.06
    POSITIVE LOGITS
     masturbation
    0.06
     aerospace
    0.06
    �
    0.06
    为了
    0.06
     freelance
    0.06
     confronted
    0.06
    Thing
    0.06
    �
    0.06
     advisers
    0.06
     thuế
    0.06
    Act Density 0.005%

    No Known Activations