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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Initiative
    -0.07
    ..↵↵
    -0.07
    뛩
    -0.07
     Brigade
    -0.07
    …”↵↵
    -0.07
     electrode
    -0.07
    acyj
    -0.07
    …↵↵↵↵
    -0.07
    号召
    -0.07
    챌
    -0.07
    POSITIVE LOGITS
    챃
    0.08
     fact
    0.07
    íg
    0.07
    ⾛
    0.07
    ichever
    0.07
     taps
    0.07
    رام
    0.07
    文中
    0.07
     לשלם
    0.07
    香蕉
    0.07
    Act Density 0.135%

    No Known Activations