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

    Neuronpedia

    INDEX
    Explanations

    mixed English and Chinese instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Trag
    -0.09
    Explosion
    -0.08
     incorporating
    -0.08
    aggreg
    -0.08
     racont
    -0.08
     gevuld
    -0.08
     বিম
    -0.08
     breakthroughs
    -0.08
     भूमि
    -0.08
     explosions
    -0.08
    POSITIVE LOGITS
     отключ
    0.15
     deaktiv
    0.13
     uninstall
    0.13
    _toggle
    0.12
     настрой
    0.12
     настройки
    0.12
     Наст
    0.12
     troubleshooting
    0.11
    Наст
    0.11
     unwanted
    0.11
    Act Density 0.043%

    No Known Activations