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

    Neuronpedia

    INDEX
    Explanations

    Adults

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Leaks
    -0.07
    电信
    -0.07
    应
    -0.06
    普惠
    -0.06
    首款
    -0.06
     pension
    -0.06
     remin
    -0.06
    €
    -0.06
    提名
    -0.06
     prison
    -0.06
    POSITIVE LOGITS
     setState
    0.07
     optionally
    0.07
    -phase
    0.07
    Moreover
    0.07
     Caribbean
    0.07
     ]).
    0.07
     snel
    0.07
    تراجع
    0.07
    _Se
    0.07
     Nonetheless
    0.07
    Act Density 0.002%

    No Known Activations