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

    Neuronpedia

    INDEX
    Explanations

    say "psy" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Taxi
    -0.07
     bombings
    -0.07
    ถนน
    -0.07
     sx
    -0.07
    .toByteArray
    -0.07
    隧道
    -0.07
     Streets
    -0.07
    珇
    -0.06
     fj
    -0.06
    zf
    -0.06
    POSITIVE LOGITS
    日常
    0.08
    שחקן
    0.07
     recogn
    0.07
     whim
    0.07
    شعور
    0.07
     WooCommerce
    0.07
     dispon
    0.06
    grim
    0.06
    裳
    0.06
     dim
    0.06
    Act Density 0.002%

    No Known Activations