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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    łą
    -0.08
     FIND
    -0.07
    稹
    -0.07
     randint
    -0.07
     trespass
    -0.07
    𝚑
    -0.07
    padł
    -0.07
    tri
    -0.07
     infra
    -0.07
     Spl
    -0.07
    POSITIVE LOGITS
     영
    0.08
     engaged
    0.07
     debates
    0.07
     sia
    0.06
    樂
    0.06
     Engagement
    0.06
    的老
    0.06
     Sek
    0.06
     non
    0.06
     sidel
    0.06
    Act Density 0.001%

    No Known Activations