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

    Neuronpedia

    INDEX
    Explanations

    beginnings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    のでしょうか
    -0.08
    私も
    -0.07
    ").↵↵
    -0.07
    @↵↵
    -0.07
    .&
    -0.07
    ⊳
    -0.07
    (action
    -0.07
     joining
    -0.07
     curso
    -0.07
    Jacob
    -0.07
    POSITIVE LOGITS
     predecess
    0.07
     outdated
    0.07
    .front
    0.07
    时辰
    0.06
    wl
    0.06
    уд
    0.06
    -through
    0.06
     thói
    0.06
     twórc
    0.06
     vitality
    0.06
    Act Density 0.031%

    No Known Activations