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

    Neuronpedia

    INDEX
    Explanations

    Delaying

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     فیلم
    -0.07
     ses
    -0.06
     тот
    -0.06
     bicycles
    -0.06
    iller
    -0.06
     Mathematics
    -0.06
    jf
    -0.06
    clients
    -0.06
     lắp
    -0.06
    acement
    -0.05
    POSITIVE LOGITS
    -CS
    0.07
    ialized
    0.06
    ейств
    0.06
     folder
    0.06
    odes
    0.06
     comb
    0.06
    )?.
    0.06
     LSM
    0.06
     endure
    0.06
     residue
    0.06
    Act Density 0.007%

    No Known Activations