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

    Neuronpedia

    INDEX
    Explanations

    is/are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hipp
    -0.07
     refuse
    -0.07
    scss
    -0.07
     rape
    -0.06
     سان
    -0.06
    <Block
    -0.06
     steril
    -0.06
     откры
    -0.06
    �
    -0.06
    <meta
    -0.06
    POSITIVE LOGITS
    เหต
    0.07
    �
    0.07
    режд
    0.07
     ㅇ
    0.06
     linked
    0.06
    delivr
    0.06
     Linked
    0.06
    غال
    0.06
     google
    0.06
     為
    0.06
    Act Density 0.182%

    No Known Activations