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

    Neuronpedia

    INDEX
    Explanations

    protect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.60
    +#+#
    -0.55
    oredCriteria
    -0.52
     Collision
    -0.48
    WebMethod
    -0.44
    rungsseite
    -0.44
     = 
    -0.43
    fuge
    -0.43
    moderator
    -0.42
    INSTAGRAM
    -0.42
    POSITIVE LOGITS
    voorbeeld
    0.58
    ities
    0.57
    новништво
    0.56
    warted
    0.55
    الحياه
    0.54
    tieth
    0.54
     referenties
    0.54
     Prev
    0.54
    Diweddarwch
    0.53
    Transkript
    0.52
    Act Density 0.044%

    No Known Activations