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

    Neuronpedia

    INDEX
    Explanations

    court filings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _closed
    -0.07
    振
    -0.07
     getters
    -0.07
     Pocket
    -0.06
     lengthy
    -0.06
     secondo
    -0.06
    :id
    -0.06
    aked
    -0.06
    <Func
    -0.06
    conomy
    -0.06
    POSITIVE LOGITS
    хови
    0.06
    รายการ
    0.06
     Ре
    0.06
    мерикан
    0.06
     �
    0.06
    、お
    0.06
     Dropbox
    0.06
    (inv
    0.06
    (<?
    0.06
    λμ
    0.06
    Act Density 0.001%

    No Known Activations