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

    Neuronpedia

    INDEX
    Explanations

    answering questions/giving instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Actually
    -0.07
     precondition
    -0.06
    )[:
    -0.06
     According
    -0.06
     baff
    -0.06
    聖
    -0.06
    ﾘ
    -0.06
     plywood
    -0.06
     متفاوت
    -0.06
    ْن
    -0.06
    POSITIVE LOGITS
    ottle
    0.07
     voyeur
    0.07
    Free
    0.06
    seys
    0.06
     luxury
    0.06
    .parts
    0.06
    lington
    0.06
     Imm
    0.06
     注意
    0.06
    UU
    0.06
    Act Density 0.068%

    No Known Activations