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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "]').
    -0.07
     Competitive
    -0.06
     Writing
    -0.06
    :UIAlert
    -0.06
    руж
    -0.06
     IOC
    -0.06
    άνω
    -0.06
    }`}↵
    -0.06
    .Progress
    -0.05
     tahmin
    -0.05
    POSITIVE LOGITS
     crian
    0.07
     ali
    0.07
    (pt
    0.07
    ้าส
    0.06
     MAY
    0.06
     посад
    0.06
    idae
    0.06
    Parm
    0.06
    _pe
    0.06
     Mét
    0.06
    Act Density 0.045%

    No Known Activations