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

    Neuronpedia

    INDEX
    Explanations

    Code/math expressions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sprung
    -0.07
     scream
    -0.07
    -finals
    -0.07
    .separator
    -0.06
    eeee
    -0.06
    的灵魂
    -0.06
     knot
    -0.06
    golden
    -0.06
    钢琴
    -0.06
    宝贝
    -0.06
    POSITIVE LOGITS
    _keys
    0.07
     Tanzania
    0.07
    ZY
    0.07
    ("
    0.07
    ὰ
    0.07
    行业
    0.07
     Duffy
    0.06
    𝘄
    0.06
    체
    0.06
    _rewards
    0.06
    Act Density 0.033%

    No Known Activations