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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    仿真
    -0.07
    都有
    -0.07
    检
    -0.07
    aguay
    -0.06
    builders
    -0.06
    肢体
    -0.06
    ﻇ
    -0.06
    ح
    -0.06
    肚子
    -0.06
    ˸
    -0.06
    POSITIVE LOGITS
    (My
    0.08
    >Welcome
    0.07
    (per
    0.07
    Пр
    0.07
    一刻
    0.07
     swift
    0.07
    躅
    0.06
     rate
    0.06
    (mid
    0.06
    _ART
    0.06
    Act Density 0.004%

    No Known Activations