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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trailer
    -0.08
    istica
    -0.08
    바이
    -0.07
     department
    -0.07
     spotify
    -0.06
    QU
    -0.06
    DISPLAY
    -0.06
     rail
    -0.06
     Naw
    -0.06
    Hel
    -0.06
    POSITIVE LOGITS
     ost
    0.06
     відпов
    0.06
    пп
    0.06
     ICMP
    0.06
     Γεν
    0.06
    Emb
    0.05
     india
    0.05
     cancelButtonTitle
    0.05
    arb
    0.05
     getInt
    0.05
    Act Density 0.053%

    No Known Activations