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

    Neuronpedia

    INDEX
    Explanations

    Street address abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .offsetHeight
    -0.07
    的理解
    -0.07
     waivers
    -0.07
    jumlah
    -0.07
     kiểm
    -0.07
     translateY
    -0.07
     וזאת
    -0.07
    KN
    -0.07
    	throws
    -0.07
    🐷
    -0.07
    POSITIVE LOGITS
    (un
    0.07
    Addr
    0.07
    (*
    0.07
    Hell
    0.07
    Frank
    0.06
    酬
    0.06
    产权
    0.06
    して
    0.06
    棕色
    0.06
     purse
    0.06
    Act Density 0.008%

    No Known Activations