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

    Neuronpedia

    INDEX
    Explanations

    -level

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     칼
    -0.07
    /part
    -0.06
     BitSet
    -0.06
    adastro
    -0.06
     Sang
    -0.06
     نشر
    -0.06
     ONLY
    -0.06
     Orion
    -0.06
     Thread
    -0.06
     декіль
    -0.06
    POSITIVE LOGITS
    ومات
    0.07
    /dev
    0.07
    ──
    0.06
    Gender
    0.06
     __________________________________
    0.06
    -content
    0.06
    .UserId
    0.06
     VERIFY
    0.06
    NODE
    0.06
    Ber
    0.06
    Act Density 0.001%

    No Known Activations