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

    Neuronpedia

    INDEX
    Explanations

    matrices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     engines
    -0.07
    (Base
    -0.07
    _content
    -0.06
     composers
    -0.06
    .have
    -0.06
    linear
    -0.06
     mind
    -0.06
    Leading
    -0.06
    collapse
    -0.06
    .um
    -0.06
    POSITIVE LOGITS
    ществ
    0.06
    clusions
    0.06
    ️
    0.06
     connections
    0.06
     appropriated
    0.06
    endif
    0.06
     Sanayi
    0.06
    Wunused
    0.06
     veterinarian
    0.05
    ineTransform
    0.05
    Act Density 0.068%

    No Known Activations