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

    Neuronpedia

    INDEX
    Explanations

    Code delimiters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ifers
    -0.07
     Jo
    -0.07
     een
    -0.07
     days
    -0.07
    ekte
    -0.07
    Iterations
    -0.06
    Jo
    -0.06
     activism
    -0.06
     kd
    -0.06
     Purch
    -0.06
    POSITIVE LOGITS
     سرمایه
    0.08
     респ
    0.07
    ="{!!
    0.07
    etSocketAddress
    0.06
    汽车
    0.06
     �
    0.06
     Поль
    0.06
    jím
    0.06
    GL
    0.06
     surre
    0.06
    Act Density 0.049%

    No Known Activations