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

    Neuronpedia

    INDEX
    Explanations

    context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _LAYOUT
    -0.07
    rotch
    -0.07
    .points
    -0.07
    ТО
    -0.06
     plum
    -0.06
    _SWAP
    -0.06
    ONY
    -0.06
     ^(
    -0.06
    WER
    -0.06
    ("#{
    -0.06
    POSITIVE LOGITS
     электр
    0.07
     offices
    0.06
     số
    0.06
     standard
    0.06
     qualify
    0.06
     assertion
    0.06
     tradition
    0.06
    -standard
    0.06
     schools
    0.06
     Option
    0.06
    Act Density 0.011%

    No Known Activations