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

    Neuronpedia

    INDEX
    Explanations

    impression

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pathway
    -0.07
    哲
    -0.07
     Zhu
    -0.06
    overe
    -0.06
     Sci
    -0.06
     사회
    -0.06
    (ob
    -0.06
     rights
    -0.06
    443
    -0.06
    Qty
    -0.06
    POSITIVE LOGITS
     impressions
    0.11
     impression
    0.10
     unexpected
    0.08
     Impress
    0.07
    Caught
    0.07
     tourists
    0.07
    IEWS
    0.07
    gressive
    0.06
     imagine
    0.06
    دم
    0.06
    Act Density 0.008%

    No Known Activations