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

    Neuronpedia

    INDEX
    Explanations

    Work

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inhibitor
    -0.07
     costumes
    -0.07
    /pro
    -0.07
    А
    -0.07
    共鸣
    -0.07
    bove
    -0.06
     loggedIn
    -0.06
     OVER
    -0.06
    ▇
    -0.06
    ⊂
    -0.06
    POSITIVE LOGITS
    äter
    0.07
    tatus
    0.07
    ?;↵↵
    0.07
    Estado
    0.07
    门前
    0.07
     Đặc
    0.07
     callers
    0.07
    @endforeach
    0.07
    ⺠
    0.07
    `
↵
    0.06
    Act Density 0.001%

    No Known Activations