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

    Neuronpedia

    INDEX
    Explanations

    senses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    روس
    -0.07
     TPP
    -0.07
    osp
    -0.07
    ulatory
    -0.06
    )):
    -0.06
     вес
    -0.06
     Louise
    -0.06
    	diff
    -0.06
     conclusions
    -0.06
    _weights
    -0.06
    POSITIVE LOGITS
    iversal
    0.07
     fictional
    0.07
     entirely
    0.06
     collide
    0.06
     omit
    0.06
    θηκε
    0.06
     выше
    0.06
    peare
    0.06
    ehler
    0.06
    masına
    0.06
    Act Density 0.014%

    No Known Activations