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

    Neuronpedia

    INDEX
    Explanations

    honey

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    edin
    -0.07
    😒
    -0.07
    得很好
    -0.07
    ⚾
    -0.07
    쌌
    -0.07
    릎
    -0.07
    _chart
    -0.07
    ysics
    -0.07
    ablo
    -0.07
     Xu
    -0.07
    POSITIVE LOGITS
     Honey
    0.08
    高额
    0.08
     pods
    0.07
     and
    0.07
    do
    0.07
    Located
    0.07
     _
↵
    0.07
    -public
    0.07
    NULL
    0.07
     Daly
    0.07
    Act Density 0.005%

    No Known Activations