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

    Neuronpedia

    INDEX
    Explanations

    ->

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Envelope
    -0.08
    SUCCESS
    -0.07
    慨
    -0.07
    电子商务
    -0.07
     jade
    -0.07
    侣
    -0.07
    旅游景区
    -0.07
     bamb
    -0.07
    .Rule
    -0.06
    _pct
    -0.06
    POSITIVE LOGITS
    パイ
    0.07
    𝙙
    0.07
     '*.
    0.07
    running
    0.07
     $(".
    0.07
    メーカー
    0.07
     funding
    0.07
    bury
    0.07
     drafts
    0.07
    finish
    0.07
    Act Density 0.004%

    No Known Activations