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

    Neuronpedia

    INDEX
    Explanations

    blog posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	mp
    -0.06
    _dtype
    -0.06
    issan
    -0.06
    LOWER
    -0.06
     róż
    -0.06
                                ↵
    -0.06
    都
    -0.05
    №
    -0.05
     روست
    -0.05
    Ini
    -0.05
    POSITIVE LOGITS
    qing
    0.07
     runtime
    0.07
    솔
    0.07
    STEP
    0.07
    IMITIVE
    0.06
    _Store
    0.06
    ontvangst
    0.06
    �
    0.06
    ाइट
    0.06
     ،
    0.06
    Act Density 0.080%

    No Known Activations