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

    Neuronpedia

    INDEX
    Explanations

    100

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .CONTENT
    -0.07
     dây
    -0.06
    .import
    -0.06
    <object
    -0.06
    OAD
    -0.06
     Jury
    -0.06
     dignity
    -0.06
     Greenwich
    -0.06
    .outer
    -0.06
    resa
    -0.06
    POSITIVE LOGITS
    agent
    0.07
    블
    0.07
    inant
    0.07
    rganization
    0.06
    pdb
    0.06
    assuming
    0.06
    bank
    0.06
     thank
    0.06
     Bers
    0.06
    chr
    0.06
    Act Density 0.000%

    No Known Activations