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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exemple
    -0.07
     disguise
    -0.07
     немного
    -0.06
     ('
    -0.06
     πρέπει
    -0.06
     automation
    -0.06
    avi
    -0.06
     усп
    -0.06
    .highlight
    -0.06
     proletariat
    -0.06
    POSITIVE LOGITS
    Rejected
    0.07
     commenter
    0.06
    mít
    0.06
    .tap
    0.06
    unch
    0.06
    Thirty
    0.06
     Jab
    0.06
     moveTo
    0.06
     freaking
    0.06
    드를
    0.06
    Act Density 0.012%

    No Known Activations