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

    Neuronpedia

    INDEX
    Explanations

    special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eps
    -0.09
    depart
    -0.08
     comparing
    -0.08
     compared
    -0.08
     attendants
    -0.08
     accompany
    -0.08
    伴
    -0.08
    ajj
    -0.08
     accompanies
    -0.08
     accompagner
    -0.08
    POSITIVE LOGITS
     interfering
    0.08
     prohibited
    0.08
     interfere
    0.08
    .proto
    0.08
     interference
    0.08
     nib
    0.08
     PRO
    0.07
     troublesome
    0.07
    /template
    0.07
     misuse
    0.07
    Act Density 0.005%

    No Known Activations