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

    Neuronpedia

    INDEX
    Explanations

    palette

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intercourse
    -0.08
     dissolve
    -0.08
    杨欢
    -0.07
    벋
    -0.07
    背景下
    -0.07
     Ln
    -0.07
    煓
    -0.07
     Likewise
    -0.07
     unnoticed
    -0.06
     rationale
    -0.06
    POSITIVE LOGITS
     blogs
    0.08
    冊
    0.07
    alerts
    0.07
     presets
    0.07
    Charts
    0.07
     empath
    0.07
    重金属
    0.07
    ो
    0.07
     throne
    0.07
    ┞
    0.06
    Act Density 0.041%

    No Known Activations