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

    Neuronpedia

    INDEX
    Explanations

    medical study results

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (open
    -0.07
     contador
    -0.06
     breeds
    -0.06
    _cnt
    -0.06
    653
    -0.06
    phrase
    -0.06
    _hits
    -0.06
     수가
    -0.06
     bonuses
    -0.06
    	ss
    -0.06
    POSITIVE LOGITS
     brow
    0.06
    .features
    0.06
    intel
    0.06
     Guests
    0.06
     от
    0.06
     عليه
    0.06
     tomto
    0.06
    .des
    0.06
     tieten
    0.06
    δυ
    0.06
    Act Density 0.033%

    No Known Activations