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

    Neuronpedia

    INDEX
    Explanations

    computer code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     вред
    -0.07
    	Method
    -0.06
    _Generic
    -0.06
     phon
    -0.06
     Jeb
    -0.06
    олева
    -0.06
    ograms
    -0.06
    .bd
    -0.06
    phem
    -0.06
     будет
    -0.06
    POSITIVE LOGITS
    Textbox
    0.07
    一
    0.06
     infusion
    0.06
     nhân
    0.06
     depleted
    0.06
     чуть
    0.06
     purchased
    0.06
     chased
    0.06
    Taking
    0.06
     NAME
    0.06
    Act Density 0.041%

    No Known Activations