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

    Neuronpedia

    INDEX
    Explanations

    recipes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     phones
    -0.07
    -0.06
    >You
    -0.06
    nis
    -0.06
    ноч
    -0.06
    	expect
    -0.06
    フォ
    -0.06
     этому
    -0.06
    ulsive
    -0.06
    LU
    -0.06
    POSITIVE LOGITS
    Validator
    0.07
     변경
    0.06
     **
    0.06
    Uid
    0.06
     "()
    0.06
    AuthToken
    0.06
     Мініст
    0.06
     olası
    0.06
     telah
    0.06
    計算
    0.06
    Act Density 0.031%

    No Known Activations