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

    Neuronpedia

    INDEX
    Explanations

    scholarly writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enclosure
    -0.06
     manip
    -0.06
     Branch
    -0.06
     Alter
    -0.06
    、お
    -0.06
    064
    -0.06
     opted
    -0.06
     atual
    -0.06
    866
    -0.06
     zah
    -0.06
    POSITIVE LOGITS
    danger
    0.06
     单
    0.06
    GBP
    0.06
    employed
    0.06
    summary
    0.06
    .callbacks
    0.06
     commercials
    0.06
    _moves
    0.06
     kâ
    0.06
    Virginia
    0.06
    Act Density 0.039%

    No Known Activations