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

    Neuronpedia

    INDEX
    Explanations

    architecture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     commemorate
    -0.06
    (skill
    -0.06
    Dados
    -0.06
    (prefix
    -0.06
     launder
    -0.06
    	java
    -0.06
     offended
    -0.06
    .addClass
    -0.06
     знаю
    -0.06
     postData
    -0.06
    POSITIVE LOGITS
    OX
    0.08
    caf
    0.07
    UFFER
    0.07
     hậu
    0.06
    .Gray
    0.06
     koje
    0.06
    kn
    0.06
     루
    0.06
     ud
    0.06
     B
    0.06
    Act Density 0.044%

    No Known Activations