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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DES
    -0.06
    upid
    -0.06
    Radians
    -0.06
     Karl
    -0.06
     gre
    -0.06
    IENT
    -0.06
    哭
    -0.06
    VAR
    -0.06
    Rot
    -0.06
     bizi
    -0.06
    POSITIVE LOGITS
    室
    0.07
     exchange
    0.07
     attendees
    0.07
    .absolute
    0.07
     exchanging
    0.07
    (Local
    0.07
    .getSize
    0.07
    _same
    0.07
     happier
    0.06
     прип
    0.06
    Act Density 0.052%

    No Known Activations