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

    Neuronpedia

    INDEX
    Explanations

    lists and bullet points

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tour
    -0.07
    �
    -0.07
    tres
    -0.06
     приобрет
    -0.06
     raise
    -0.06
     ر
    -0.06
     contraseña
    -0.06
    汗
    -0.06
     klub
    -0.06
     "\""
    -0.06
    POSITIVE LOGITS
     humming
    0.07
     위
    0.06
    .xx
    0.06
     Wass
    0.06
     UserProfile
    0.06
    .case
    0.06
    iasi
    0.06
     بسي
    0.06
     요
    0.06
     sis
    0.06
    Act Density 0.011%

    No Known Activations