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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Relative
    -0.07
     Raleigh
    -0.07
    ithe
    -0.06
     زوج
    -0.06
    .o
    -0.06
    应该
    -0.06
     Mafia
    -0.06
    ่ง
    -0.06
     persuade
    -0.06
    <V
    -0.06
    POSITIVE LOGITS
    xford
    0.07
    FLT
    0.07
    .question
    0.07
    txt
    0.06
     Dank
    0.06
    WP
    0.06
    oine
    0.06
    �
    0.06
    -site
    0.06
     Agriculture
    0.06
    Act Density 0.000%

    No Known Activations