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

    Neuronpedia

    INDEX
    Explanations

    book

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	W
    -0.07
    🐡
    -0.07
    IGH
    -0.07
    mouseout
    -0.07
    haven
    -0.07
    ⁇
    -0.07
     ARISING
    -0.07
     matrices
    -0.07
     tamil
    -0.07
     deviations
    -0.07
    POSITIVE LOGITS
    さんが
    0.07
     Rocket
    0.07
    aring
    0.06
    (scanner
    0.06
     ecosystem
    0.06
     skill
    0.06
    ጁ
    0.06
     constrain
    0.06
    這樣的
    0.06
    chema
    0.06
    Act Density 0.064%

    No Known Activations