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

    Neuronpedia

    INDEX
    Explanations

    keep

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (@(
    -0.07
    issant
    -0.06
     thị
    -0.06
     BitSet
    -0.06
    .startActivity
    -0.06
     wf
    -0.06
     verte
    -0.06
    ñas
    -0.06
    ประถม
    -0.06
     Nhà
    -0.06
    POSITIVE LOGITS
     warns
    0.07
     payer
    0.06
    ened
    0.06
     Helps
    0.06
     workforce
    0.06
     Deadline
    0.06
    《
    0.06
    After
    0.06
    download
    0.06
     Slate
    0.06
    Act Density 0.000%

    No Known Activations