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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /chat
    -0.07
    ackle
    -0.07
    peng
    -0.07
     classifications
    -0.06
    workspace
    -0.06
    pci
    -0.06
     testimony
    -0.06
     mee
    -0.06
     RANGE
    -0.06
    consum
    -0.06
    POSITIVE LOGITS
     đ�
    0.07
    原因
    0.06
    Miami
    0.06
    .↵↵↵↵↵
    0.06
     Albany
    0.06
     ninguna
    0.06
     بیمار
    0.06
     selectors
    0.06
    (Dense
    0.06
    ленные
    0.06
    Act Density 0.000%

    No Known Activations