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

    Neuronpedia

    INDEX
    Explanations

    system partition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ighbor
    -0.09
    ระดับ
    -0.08
     строй
    -0.08
     Formen
    -0.08
     schlim
    -0.08
    भी
    -0.08
     Goes
    -0.08
     kompl
    -0.08
    pares
    -0.07
     manchen
    -0.07
    POSITIVE LOGITS
     dédiée
    0.10
    Dedicated
    0.09
     Dedicated
    0.09
     dedicated
    0.08
     dédié
    0.08
    Designation
    0.08
    BUF
    0.08
     dedicada
    0.08
     राख
    0.08
     chứa
    0.08
    Act Density 0.003%

    No Known Activations