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

    Neuronpedia

    INDEX
    Explanations

    democratic reform

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    弹性
    -0.07
    RYPTO
    -0.07
    amsung
    -0.07
     bloody
    -0.07
    ()->
    -0.07
     Amanda
    -0.06
     Polly
    -0.06
     Rene
    -0.06
     bacteria
    -0.06
    }-
    -0.06
    POSITIVE LOGITS
    .ws
    0.07
    时代的
    0.07
    MZ
    0.07
    ؤمن
    0.07
     pathways
    0.07
    之路
    0.07
    _general
    0.07
    直
    0.06
     paths
    0.06
    𬇙
    0.06
    Act Density 0.046%

    No Known Activations