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

    Neuronpedia

    INDEX
    Explanations

    Core

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     זו
    -0.08
    辙
    -0.08
    atedRoute
    -0.08
    �
    -0.08
    ☼
    -0.07
    ⽅
    -0.07
    ㅈ
    -0.07
    舂
    -0.07
     ú
    -0.07
     חדשים
    -0.07
    POSITIVE LOGITS
    ooting
    0.08
     Ow
    0.07
    AIT
    0.07
    透过
    0.07
    퉈
    0.07
    _segments
    0.07
    人们的
    0.07
    launch
    0.07
    rimon
    0.07
    uerdo
    0.07
    Act Density 0.001%

    No Known Activations