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

    Neuronpedia

    INDEX
    Explanations

    theatrical works

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    几
    -0.07
    (mock
    -0.06
    اطر
    -0.06
    вами
    -0.06
     MCC
    -0.06
    ίος
    -0.06
     ORM
    -0.06
    简
    -0.06
     одним
    -0.06
     Parker
    -0.06
    POSITIVE LOGITS
     Challenger
    0.07
     Fog
    0.07
    chain
    0.06
    Internet
    0.06
    zeug
    0.06
    λω
    0.06
     counts
    0.06
    uck
    0.06
     posed
    0.06
    .PERMISSION
    0.06
    Act Density 0.008%

    No Known Activations