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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     condemning
    -0.06
     statutory
    -0.06
    -setting
    -0.06
     reconsider
    -0.06
    tube
    -0.06
     crem
    -0.06
     chairs
    -0.06
    proposal
    -0.06
    tip
    -0.06
    website
    -0.06
    POSITIVE LOGITS
     Missile
    0.07
     Unlike
    0.06
    -enh
    0.06
     채용
    0.06
    .entity
    0.06
     timp
    0.06
     ActionListener
    0.06
     Paginator
    0.06
    OLUMNS
    0.06
     Antib
    0.06
    Act Density 0.000%

    No Known Activations