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

    Neuronpedia

    INDEX
    Explanations

    Technical diagrams

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     buffering
    -0.08
    symbols
    -0.07
     Stars
    -0.07
    文学
    -0.06
     appearances
    -0.06
    ói
    -0.06
    CAT
    -0.06
    INFO
    -0.06
     operation
    -0.06
    	hit
    -0.06
    POSITIVE LOGITS
     kullanılan
    0.06
    idepress
    0.06
    (enable
    0.06
     расход
    0.06
    omik
    0.06
    ayload
    0.06
    οκ
    0.06
    افه
    0.06
     pumpkin
    0.06
    abilidade
    0.05
    Act Density 0.001%

    No Known Activations