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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "***
    -0.07
     Questions
    -0.07
     Chennai
    -0.07
    atisation
    -0.07
     Officers
    -0.07
    ⚬
    -0.07
    /AFP
    -0.07
     Abbas
    -0.07
    펠
    -0.07
    uelles
    -0.07
    POSITIVE LOGITS
     processing
    0.07
    cam
    0.07
     tiện
    0.06
    Cow
    0.06
    眼镜
    0.06
    期刊
    0.06
    �
    0.06
    ドレス
    0.06
    ToMany
    0.06
    .filter
    0.06
    Act Density 0.019%

    No Known Activations