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

    Neuronpedia

    INDEX
    Explanations

    dual

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     %%
    -0.07
    汀
    -0.07
     rf
    -0.07
    愤怒
    -0.07
    WithIdentifier
    -0.07
    ground
    -0.07
    مفاوضات
    -0.07
     knockout
    -0.06
    记者
    -0.06
     آلاف
    -0.06
    POSITIVE LOGITS
    については
    0.07
    �
    0.07
    �
    0.07
     enorm
    0.07
     CSRF
    0.06
    .border
    0.06
    (pair
    0.06
     getDescription
    0.06
    decor
    0.06
    ROADCAST
    0.06
    Act Density 0.005%

    No Known Activations