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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     licens
    -0.07
     котором
    -0.06
    면
    -0.06
    doing
    -0.06
     있고
    -0.06
    (un
    -0.06
    άννης
    -0.06
     sou
    -0.06
     waves
    -0.06
    tober
    -0.06
    POSITIVE LOGITS
     "
    0.08
     “
    0.07
    cerpt
    0.07
     “…
    0.06
    」「
    0.06
    .crt
    0.06
    bben
    0.06
    ，“
    0.06
    ческого
    0.06
    acyj
    0.06
    Act Density 0.026%

    No Known Activations