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

    Neuronpedia

    INDEX
    Explanations

    interest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _misc
    -0.09
    FILE
    -0.08
     Psi
    -0.08
     produtividade
    -0.08
     CPU
    -0.08
     Skyline
    -0.08
    powers
    -0.07
    .linear
    -0.07
     RBC
    -0.07
     Ded
    -0.07
    POSITIVE LOGITS
     empathy
    0.09
     empath
    0.09
    Verse
    0.08
     അഭിപ്രായ
    0.08
     conversational
    0.08
    别人
    0.08
     apology
    0.08
     excuse
    0.08
     vielfält
    0.08
    ความคิดเห็น
    0.08
    Act Density 0.085%

    No Known Activations