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

    Neuronpedia

    INDEX
    Explanations

    consent/permission

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UBLISH
    -0.07
     EVE
    -0.07
     Western
    -0.07
    (names
    -0.06
     casualties
    -0.06
     �
    -0.06
     Initializes
    -0.06
    (weights
    -0.06
     واج
    -0.06
    척
    -0.06
    POSITIVE LOGITS
    portun
    0.07
    Uni
    0.06
    .checkBox
    0.06
     skup
    0.06
    тесь
    0.06
     athletics
    0.06
    ****
    0.06
    ORG
    0.06
    _top
    0.06
     Jazeera
    0.06
    Act Density 0.004%

    No Known Activations