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

    Neuronpedia

    INDEX
    Explanations

    commas and periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thereof
    -0.07
     filmes
    -0.07
     ctr
    -0.06
     distribution
    -0.06
    •
    -0.06
     customer
    -0.06
     treatment
    -0.06
     rapidement
    -0.06
     mg
    -0.06
     axios
    -0.06
    POSITIVE LOGITS
     рес
    0.07
    orent
    0.07
    :numel
    0.06
     charisma
    0.06
    ANGLES
    0.06
    getDate
    0.06
     Grey
    0.06
    .Minute
    0.06
     základní
    0.06
     afirm
    0.06
    Act Density 0.025%

    No Known Activations