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

    Neuronpedia

    INDEX
    Explanations

    Software

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     travel
    -0.08
     tour
    -0.07
     ellipse
    -0.07
     listing
    -0.06
     enrich
    -0.06
     Travel
    -0.06
     occupants
    -0.06
     mixing
    -0.06
     PAY
    -0.06
    inter
    -0.06
    POSITIVE LOGITS
     conditioned
    0.19
    род
    0.08
     remedies
    0.07
     Shirley
    0.07
    ัตว
    0.07
    /id
    0.07
    َه
    0.07
    <$
    0.07
     것으로
    0.06
    -shadow
    0.06
    Act Density 0.002%

    No Known Activations