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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ostensibly
    -0.07
    вших
    -0.07
    ophil
    -0.07
     Mit
    -0.07
    หน
    -0.07
     NSLocalizedString
    -0.07
    .ApplyResources
    -0.07
     MARK
    -0.06
     Approximately
    -0.06
     CODE
    -0.06
    POSITIVE LOGITS
    퉤
    0.07
     tir
    0.07
    Deal
    0.07
    (register
    0.07
     reopened
    0.07
    不动产
    0.07
    听取
    0.07
    tica
    0.07
    cer
    0.07
    再多
    0.07
    Act Density 0.005%

    No Known Activations