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

    Neuronpedia

    INDEX
    Explanations

    ic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exhaustion
    -0.09
     metall
    -0.07
    ולד
    -0.07
    最基本
    -0.07
     refunded
    -0.07
     Forrest
    -0.07
    licated
    -0.07
    戆
    -0.07
     reward
    -0.07
     greet
    -0.07
    POSITIVE LOGITS
    ytic
    0.08
    ம
    0.07
     пользоват
    0.07
     strategically
    0.07
    avirus
    0.07
     CR
    0.07
    visual
    0.07
     discrepan
    0.07
     jur
    0.07
    ดร
    0.07
    Act Density 0.001%

    No Known Activations